We put the Xiaomi 17 Ultra through our rigorous DXOMARK Camera test suite to measure its performance in photo, video, and zoom quality from an end-user perspective. This article breaks down how the device fared in a variety of tests and several common use cases and is intended to highlight the most important results of our testing with an extract of the captured data.
Use case scores indicate the product performance in specific situations. They are not included in the overall score calculations.
BEST 169
Top score %s
Portrait
Portrait photos of either one person or a group of people
BEST 185
Top score %s
Outdoor
Photos & videos shot in bright light conditions (≥1000 lux)
BEST 180
Top score %s
Indoor
Photos & videos shot in good lighting conditions (≥100lux)
BEST 149
Top score %s
Lowlight
Photos & videos shot in low lighting conditions (<100 lux)
BEST 159
Top score %s
Zoom
Photos and videos captured using zoom (more than 1x)
Pros
Very good trade-off between texture and noise, with the exception of low light video
Excellent tele zoom
Nice color rendering and accurate white balance in photo and video
Natural looking bokeh mode with very good subject isolation
Cons
Autofocus lack of smoothness in video, and depth of field is very limited for group pictures
Exposure and white balance instabilities are occasionally visible
The Xiaomi 17 Ultra delivers an excellent performance in the DXOMARK Camera tests. In many test areas it is a significant upgrade over its predecessor 15 Ultra and is getting close to the very best flagship devices on the market – without quite matching them, however. Photo performance is particularly impressive. Overall photo results are strong but the camera really shines when using the tele zoom or capturing portrait images.
Video performance is not quite on the same high level. Results are good but the when capturing moving images the Xiaomi 17 Ultra lags slightly behind the best-in-class competitors, still showing some issues that have been eliminated on class-leading video devices.
Xiaomi 17 Ultra – Excellent portrait shots
BEST 149
Top score Vivo X300 Pro
Lowlight
The Xiaomi 17 Ultra is an excellent photo performer in low light and delivers outstanding night shots with high levels of detail in most situations. This is not quite true for the video mode, where the phone falls short of expectations and stands as one of the weakest performers among this year’s flagship phones.
BEST 169
Top score Huawei Pura 80 Ultra
Portrait
The new Xiaomi flagship does not quite surpass the best in class but is still an outstanding option for portraiture, with excellent subject exposure, remarkably high levels of detail, even with moving subjects, and a very good bokeh mode.
BEST 159
Top score Vivo X300 Pro
Zoom
Zoom is one of the Xiaomi 17 Ultra’s strongest areas, particularly when it comes to tele zoom. Thanks to the powerful telephoto configuration, it ranks within the top three devices for this category, coming very close to the Huawei Pura 80 Ultra and the Vivo X200 Ultra, which occupy the top spots of the ranking.
Test summary
About DXOMARK Camera tests: DXOMARK’s camera evaluations take place in laboratories and real-world situations using a wide variety of use-cases. The scores rely on objective tests for which the results are calculated directly using measurement software in our laboratory setups, and on perceptual tests where a sophisticated set of metrics allow a panel of image experts to compare aspects of image quality that require human judgment. Testing a smartphone involves a team of engineers and technicians for about a week. Photo and Video quality are scored separately and then combined into an overall score for comparison among the cameras in different devices. For more information about the DXOMARK Camera protocol, click here. More details on smartphone camera scores are available here. The following section gathers key elements of DXOMARK’s exhaustive tests and analyses. Full performance evaluations are available upon request. Please contact us on how to receive a full report.
Xiaomi 17 Ultra Camera Scores
This graph compares DXOMARK photo and video scores between the tested device and references. Average and maximum scores of the price segment are also indicated. Average and maximum scores for each price segment are computed based on the DXOMARK database of devices tested.
For scoring and analysis, DXOMARK engineers capture and evaluate more than 3,800 test images in controlled lab environments as well as outdoor, indoor and low-light natural scenes, using the camera’s default settings. The photo protocol is designed to take into account the main use cases and is based on typical shooting scenarios, such as portraits, landscape and zoom photography. The evaluation is performed by visually inspecting images against a reference of natural scenes, and by running objective measurements on images of charts captured in the lab under different lighting conditions from 0.1 to 10,000+ lux and color temperatures from 2,300K to 6,500K.
The Xiaomi 17 Ultra is an excellent smartphone for still imaging, thanks in part to the impressive camera specs, that include a large 1‑inch sensor in the primary module, a sliding 75‑100mm equivalent tele module with periscope design and a very large 200 MP sensor, as well as a 50MP ultra-wide camera. Additional components, such as PDAF, laser autofocus, ToF sensing, and a color spectrum sensor further support the capture pipeline.
Overall, the camera operates almost flawlessly in photo mode, with excellent performance across the entire focal range, from ultra-wide to long tele zoom. Our testers only noticed some focus‑related decision errors and the naturally limited depth of field.
The primary camera module excels in areas such as texture and noise. Night photography is a particular strength, but some small issues remain and prevent the Xiaomi from consistently reaching the very top of the category rankings. This includes occasional weaknesses at specific zoom settings, the handling of some artifacts, and some contrast inaccuracies in exposure rendering.
Main
171
Xiaomi 17 Ultra
184
Huawei Pura 80 Ultra
Huawei Pura 80 Ultra
Xiaomi 17 Ultra Photo scores
The photo Main tests analyze image quality attributes such as exposure, color, texture, and noise in various light conditions. Autofocus performances and the presence of artifacts on all images captured in controlled lab conditions and in real-life images are also evaluated. All these attributes have a significant impact on the final quality of the images captured with the tested device and can help to understand the camera's main strengths and weaknesses at 1x.
The Xiaomi 17 Ultra delivers a strong overall performance in the DXOMARK Camera tests, with particularly high scores in the color, texture, and noise categories. Still images tend to be very bright, sometimes approaching the upper limit of acceptable exposure, yet dynamic range remains wide with good highlight retention. White balance is generally accurate across lighting conditions, but color rendering can occasionally appear slightly muted when viewing images on an HDR display. Texture performance is among the best we have seen. High levels of detail even on moving subjects make the Xiaomi an excellent choice for sports, pet, and family photography. Noise is extremely well controlled, but the aggressive noise reduction can introduce texture artifacts and quantization in areas of plain color.
Autofocus is the camera’s main weakness. It is fast in the, lab with almost no shutter lag, but in real-life scenes it often locks onto the second-closest subject to the camera instead of the closest one. The shallow depth of field limits sharpness of background subjects in group shots. In addition, the Super Macro mode does not provide sufficient magnification to achieve true macro results.
Exposure is one of the key attributes for technically good pictures. The main attribute evaluated is the brightness level of the main subject through various use cases such as landscape, portrait, or still life. Other factors evaluated are the global contrast and the ability to render the dynamic range of the scene (ability to render visible details in both bright and dark areas). When the camera provides Photo HDR format, the images are analyzed with a visualization on an HDR reference monitor, under reference conditions specified in the ISO-22028-5 standard. Repeatability is also important because it demonstrates the camera's ability to provide the same rendering when shooting several images of the same scene.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Eugene)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Eugene)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Eugene)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Eugene)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Still image exposure is solid but lags slightly behind the best in class. The camera achieves a wide dynamic range and good highlight retention, even when shooting in low light. Images in general and skin tones specifically are among the brightest in the ultra premium segment, with high contrast levels. The bright skin tone rendering is also applied to dark skin tones, sometimes approaching the upper limit of acceptable exposure in our lab.
Contrast handling leaves some room for improvement, with overly strong local contrast in some landscape scenes, as well as contrast issues in backlit scenes, in both test laboratory and real-life scenes. In such conditions our testers often observed compressed highlight contrast and flare artifacts reducing shadow contrast, making for a slightly unnatural look of the image.
Xiaomi 17 Ultra – Accurately exposed face, good highlight retention in background
Color is one of the key attributes for technically good pictures. The image quality attributes analyzed are skin-tone rendering, white balance, color shading, and repeatability. For color and skin tone rendering, we penalize unnatural colors according to results gathered in various studies and consumer insights while respecting the manufacturer's choice of color signature.
The Xiaomi 17 Ultra does well for color. White balance is generally accurate in daylight and under typical indoor lighting. In low light images a slightly warm, but pleasant cast can be noticeable. Overall, color rendering is reliable, but in some scenes color can appear a little muted, especially under daylight and in low light.
Xiaomi 17 Ultra – Neutral white balance, nice skin tones
Autofocus tests concentrate on focus accuracy, focus repeatability, shooting time delay, and depth of field. Shooting delay is the difference between the time the user presses the capture button and the time the image is actually taken. It includes focusing speed and the capability of the device to capture images at the right time, what is called 'zero shutter lag' capability. Even if a shallow depth of field can be pleasant for a single subject portrait or close-up shot, it can also be a problem in some specific conditions such as group portraits; Both situations are tested. Focus accuracy is also evaluated in all the real-life images taken, from infinity to close-up objects and in low light to outdoor conditions.
Autofocus irregularity and speed: 100Lux Δ4EV TL84 Handheld
This graph illustrates focus accuracy and speed as well as zero shutter lag capability by showing the edge acutance versus the shooting time measured on the AFHDR setup on a series of pictures. All pictures were taken in one light condition and indicated illuminant, 500ms after the defocus. The edge acutance is measured on the four edges of the Dead Leaves chart, and the shooting time is measured on the LED Universal Timer.
Xiaomi 17 Ultra – Focus on background subject, limited depth of field for group shots
Xiaomi 15 Ultra – Focus on foreground subject, wider depth of field results in better detail on second subject
Apple iPhone 17 Pro – Slightly limited depth of field
Texture tests analyze the level of details and the texture of subjects in the images taken in the lab as well as in real-life scenarios. For natural shots, particular attention is paid to the level of details in the bright and dark areas of the image. Objective measurements are performed on chart images taken in various lighting conditions from 0.1 to 10,000+ lux and different kinds of dynamic range conditions. The charts used are the proprietary DXOMARK chart (DMC), and the Dead Leaves chart. We also have an AI based metric for the level of details on our realistic mannequins Eugene and Diana.
DXOMARK CHART (DMC) detail preservation score vs lux levels for handheld conditions
This graph shows the evolution of the DMC detail preservation score with the level of lux, for two holding conditions. DMC detail preservation score is derived from an AI-based metric trained to evaluate texture and details rendering on a selection of crops of our DXOMARK chart.
The Xiaomi 17 Ultra is one of the very best devices for texture we have tested to date. High levels of fine detail are maintained across most light conditions. The camera’s ability to preserve sharpness on moving subjects is particularly impressive. This is clearly visible on our motion charts in the lab, and confirmed by real-life results.
Combined with the fast and reactive autofocus system, this makes the Xiaomi 17 Ultra an excellent option for shooting scenes with subjects in motion, for example sports, pets, or family moments with children.
One minor drawback is worth mentioning, though. While in low light the level of captured detail is mostly good, textures can look a little unnatural. Particularly moving subjects can look smoothed by noise reduction.
Noise tests analyze various attributes of noise such as intensity, chromaticity, grain, structure on real-life images as well as images of charts taken in the lab. For natural images, particular attention is paid to the noise on faces, landscapes, but also on dark areas and high dynamic range conditions. Noise on moving objects is also evaluated on natural images. Objective measurements are performed on images of charts taken in various conditions from 0.1 to 10000 lux and different kinds of dynamic range conditions. The chart used is the Dead Leaves chart and the standardized measurement such as Visual Noise derived from ISO 15739.
Visual noise evolution with illuminance levels in handheld condition
This graph shows the evolution of visual noise metric with the level of lux in handheld condition. The visual noise metric is the mean of visual noise measurement on all patches of the Dead Leaves chart in the AFHDR setup. DXOMARK visual noise measurement is derived from ISO15739 standard.
Noise is another one of the Xiaomi’s strong points. Like for texture, it is among the top two devices for this category. With only a few minor exceptions, noise is virtually absent in real-life scenes. However, the very aggressive noise reduction can have some subtle side effects. Slight texture artifacts can make an appearance, as well as some quantization in areas of plain color. Despite these minor issues, the overall noise performance remains excellent.
The artifacts evaluation looks at flare, lens shading, chromatic aberrations, geometrical distortion, edges ringing, halos, ghosting, quantization, unexpected color hue shifts, among others type of possible unnatural effects on photos. The more severe and the more frequent the artifact, the higher the point deduction on the score. The main artifacts observed and corresponding point loss are listed below.
Bokeh is tested in one dedicated mode, usually portrait or aperture mode, and analyzed by visually inspecting all the images captured in the lab and in natural conditions. The goal is to reproduce portrait photography comparable to one taken with a DLSR and a wide aperture. The main image quality attributes paid attention to are depth estimation, artifacts, blur gradient, and the shape of the bokeh blur spotlights. Portrait image quality attributes (exposure, color, texture) are also taken into account.
The Xiaomi 17 Ultra bokeh mode is among the very best we have seen to date. Subject segmentation in real-life scenes is particularly impressive, with highly accurate cutouts, even of very fine detail, such as hair. Background blur is strong and aesthetically pleasing, It is complemented by round, well-contrasted spotlight rendering that gives bokeh mode images a convincing optical depth-of-field effect.
Under controlled lab conditions segmentation is a little more inconsistent, with some failures in scenes with busy backgrounds. This is why the Xiaomi could not quite match the Vivo X300 Pro’s top score in this test category.
Default face beautification is worth mentioning as well. It is applied subtly and intelligently, preserving high levels of facial detail while smoothing blemishes. Unless you know the subject well, this is hardly noticeable, but in some situations, the processing can introduce minor color quantization. It appears in the form of small areas of plain color on the skin and makes skin texture look slightly unnatural in the affected areas.
Xiaomi 17 Ultra - Bokeh mode
Xiaomi 17 Ultra - Good segmentation of fine detail (hair), skin smoothing
Xiaomi 15 Ultra - Bokeh mode
Xiaomi 15 Ultra - Good segmentation but some fine hair strands are blurred
Apple iPhone 17 Pro - Bokeh mode
Apple iPhone 17 Pro - Good segmentation, slight lack of detail
All image quality attributes are evaluated at focal lengths from approximately 40 mm to 300 mm, with particular attention paid to texture and detail. The score is derived from a number of objective measurements in the lab and perceptual analysis of real-life images.
Xiaomi 17 Ultra Telephoto Scores
This graph illustrates the relative scores for the different zoom ranges evaluated. The abscissa is expressed in 35mm equivalent focal length.
When tele-zooming, the Xiaomi 17 Ultra provides excellent zoom continuity, with good detail from the main camera all the way to extra‑long tele settings. Compared to the competition, detail is especially good at short and mid-range tele, between 35 and 75mm equivalent focal length, before the camera switches to the dedicated tele module. Detail is still good at long tele up to 200mm equivalent. Where the 17 Ultra falls slightly short of the best devices in the ultra premium segment is mid-range tele, from 85-150mm equivalent focal length.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
These tests analyze the performance of the ultra-wide camera at several focal lengths from 12 mm to 20 mm. All image quality attributes are evaluated, with particular attention paid to such artifacts as chromatic aberrations, lens softness, and distortion. Pictures below are an extract of tested scenes.
Xiaomi 17 Ultra Ultra-Wide Scores
This graph illustrates the relative scores for the different zoom ranges evaluated. The abscissa is expressed in 35mm equivalent focal length.
The wide camera module offers a shortest focal length close to 14mm equivalent. Performance is very solid, ranking the Xiaomi among the top five devices for this category. The texture/noise trade-off is excellent in real-life scenes. Good exposure and color contribute to the overall good image quality and are in line with the primary camera output. This said, when zooming in on the ultra-wide camera just to the point before the primary takes over (around 18mm equivalent), there is a slight drop in detail which we did not observe on the best performing devices for ultra-wide.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
Xiaomi 17 Ultra – High levels of detail, nice colors
DXOMARK engineers capture and evaluate almost 3 hours of video in controlled lab environments and in natural low-light, indoor and outdoor scenes, using the camera’s default settings. The evaluation consists of visually inspecting natural videos taken in various conditions and running objective measurements on videos of charts recorded in the lab under different conditions from 0.1 to 10000+ lux and color temperatures from 2,300K to 6,500K.
The Xiaomi 17 Ultra offers a wide range of video recording options, including up to 8K resolution and multiple frame‑rates at 4K. Dolby Vision HDR is available at 4K/60fps. Our tests were conducted at 4K/60fps with Dolby HDR, as these settings offered the best overall balance between exposure, color accuracy, and stabilization.
At these settings, video performance is solid and dependable. Target exposure is generally accurate, with a fairly wide dynamic range in most daylight and indoor scenes. Color rendering is usually stable and reliable, offering natural‑looking hues and consistent skin‑tones. The camera also delivers a strong texture/noise trade-off, with good texture preservation and well‑controlled noise.
The imaging hardware, in combination with the Leica‑tuned processing, provides clean results, but overall video performance still lags slightly behind the iPhone 17 Pro and the best Android devices. For example, stepping can be noticeable in autofocus transitions, face tracking is occasionally lost and exposure and white‑balance transitions can be slightly unstable, especially with sudden changes in lighting. Thanks to the 200MP periscope tele module, accurate color and good detail are maintained during zooming, but transitions between modules are noticeable.
Main
164
Xiaomi 17 Ultra
186
Apple iPhone 17 Pro
Apple iPhone 17 Pro
Xiaomi 17 Ultra Video scores
Video Main tests analyze the same image quality attributes as for still images, such as exposure, color, texture, or noise, in addition to temporal aspects such as speed, and smoothness and stability of exposure, white balance, and autofocus transitions.
Exposure tests evaluate the brightness level of the main subject, the global contrast and the ability to render the dynamic range of the scene (ability to render visible details in both bright and dark areas). When the camera provides Video HDR format, the videos are analyzed with a visualization on an HDR reference monitor, under reference conditions specified in the metadata. Stability and temporal adaption of the exposure are also analyzed.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Brightness on face with illuminance levels (Diana)
These graphs represent the output level on the face measured on the images captured by the device under test in multiple lighting conditions on the AFHDR Portrait setup. We show here the intensity measured on the forehead of the realistic mannequin, for a picture displayed on a HDR monitor in standard ISO/TS 22028-5 playback conditions. The multiple lighting conditions of the scene are characterized by the illumination level in lux and the relative brightness of the backlit panel simulating high dynamic range conditions. Delta EV specifies the difference of luminance in stops between the face and the light panel simulating HDR conditions. The intensity is measured in JND derived from the ICtCp color space.
Video exposure is generally reliable, with accurate target exposure in most scenes and a fairly wide dynamic range that preserves highlight and shadow detail alike. Occasional exposure instabilities with sudden changes in the scene or lighting can be noticeable. Overall brightness is well controlled, but temporal flicker can appear under challenging mixed lighting.
Xiaomi 17 Ultra – Good exposure and wide dynamic range.
Image-quality color analysis looks at color rendering, skin-tone rendering, white balance, color shading, stability of the white balance and its adaption when light is changing.
Color rendering in video mode is usually stable and dependable, with natural‑looking hues and consistent skin tones in outdoor and indoor conditions. White balance is mostly accurate but can drift when lighting changes abruptly, resulting in short‑lived color casts before correction. This said, in general use, color rendering remains pleasing and coherent.
Xiaomi 17 Ultra – Slight white balance transition issues, nice color rendering
Xiaomi 15 Ultra – Slight white balance transition issues, nice color rendering
Apple iPhone 17 Pro – Slight white balance transition issues, nice color rendering
For video, autofocus tests concentrate on focus accuracy, focus stability and analysis of convergence regarding speed and smoothness.
Autofocus accuracy is good, but stepping can be noticeable during transitions between subjects. Focus lock can be lost momentarily during face tracking, especially with moving subjects or sudden changes in focus distance. On the plus side, static scenes are rendered sharply.
Xiaomi 17 Ultra – Subject mostly in focus, slight loss of focus when getting closer
Xiaomi 15 Ultra – Subject in focus, slight loss of focus when getting closer
Texture tests analyze the level of details and texture of the real-life videos as well as the videos of charts recorded in the lab. Natural videos recordings are visually evaluated, with particular attention paid to the level of details in the bright and areas as well as in the dark. Objective measurements are performed of images of charts taken in various conditions from 0.1 to 10000 lux. The charts used are the DXOMARK chart (DMC) and Dead Leaves chart.
Detail rendition in video is a strong point of the 17 Ultra. Fine textures are preserved well in both outdoor and indoor scenes. The camera avoids excessive sharpening halos, keeping edges natural while maintaining clarity. Low light detail is competitive, but slight softening can occur to prevent noise amplification.
DXOMARK CHART (DMC) detail preservation video score vs lux levels
This graph shows the evolution of the DMC detail preservation video score with the level of lux in video. DMC detail preservation score is derived from an AI-based metric trained to evaluate texture and details rendering on a selection of crops of our DXOMARK chart.
Noise tests analyze various attributes of noise such as intensity, chromaticity, grain, structure, temporal aspects on real-life video recording as well as videos of charts taken in the lab. Natural videos are visually evaluated, with particular attention paid to the noise in the dark areas and high dynamic range conditions. Objective measurements are performed on the videos of charts recorded in various conditions from 0.1 to 10000 lux. The chart used is the DXOMARK visual noise chart.
Noise is overall well controlled, remaining low at mid‑to‑bright light levels and only increasing modestly under typical indoor lighting. In low light, some luminance noise is noticeable in areas of plain color, but temporal noise filtering keeps it from becoming too intrusive. Chroma noise is rare and generally unobtrusive.
Spatial visual noise evolution with the illuminance level
This graph shows the evolution of spatial visual noise with the level of lux. Spatial visual noise is measured on the visual noise chart in the video noise setup. DXOMARK visual noise measurement is derived from ISO15739 standard.
Temporal visual noise evolution with the illuminance level
This graph shows the evolution of temporal visual noise with the level of lux. Temporal visual noise is measured on the visual noise chart in the video noise setup.
Stabilization evaluation tests the ability of the device to stabilize footage thanks to software or hardware technologies such as OIS, EIS, or any others means. The evaluation looks at residual motion, smoothness, jello artifacts and residual motion blur on walk and run use cases in various lighting conditions. The video below is an extract from one of the tested scenes.
Video stabilization is effective when walking and panning during recording. Framing is stable and camera shake within acceptable limits. This said, fast motion or abrupt stops can introduce micro‑jitter. Overall though, stabilization allows for confident handheld use without major artifacts.
Artifacts are evaluated with MTF and ringing measurements on the SFR chart in the lab as well as frame-rate measurements using the LED Universal Timer. Natural videos are visually evaluated by paying particular attention to artifacts such as aliasing, quantization, blocking, and hue shift, among others. The more severe and the more frequent the artifact, the higher the point deduction from the score. The main artifacts and corresponding point loss are listed below.
All image quality attributes are evaluated at focal lengths from approximately 12 mm to 300 mm, with particular attention paid to texture and smoothness of the zooming effect. The score is derived from a number of objective measurements in the lab and perceptual analysis of real-life video recordings.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
DXOMARK CHART (DMC) detail preservation score per focal length
This graph shows the evolution of the DMC detail preservation score with respect to the full-frame equivalent focal length for different light conditions. The x-axis represents the equivalent focal length measured for each corresponding shooting distance and the y-axis represents the maximum details preservation metric score: higher value means better quality. Large dots correspond to zoom ratio available in the user interface of the camera application.
The Xiaomi 17 Ultra does well when zooming in video mode. Color rendering remains accurate and detail holds up well as you move through the zoom range, helped by the dedicated tele module. This said, transition smoothness still lags behind the best in class. There are noticeable jumps when switching between camera modules and our testers observed occasional exposure or white‑balance stepping.
Medium‑range zoom settings deliver the overall most consistent results. At the long end of the tele stabilization and noise control remain competent but not class‑leading, and fine textures can show mild smoothing. Overall, zoom footage is very usable and coherent, but seamless ramps and cross‑module consistency have room for improvement.
Xiaomi 17 Ultra – Good detail with video zoom, slight jump between camera modules
Xiaomi 15 Ultra – Good detail with video zoom, slight jump between camera modules
Apple iPhone 17 Pro – Good detail in video zoom , smooth transitions