With the increasing importance of mobile camera quality in modern smartphones, growing attention has been directed toward computational photography and advanced image signal processing (ISP) algorithms aimed at enhancing various perceptual attributes of captured images. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can reconstruct RGB photos from RAW Bayer camera data while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale Fujifilm UltraISP dataset consisting of RAW-RGB image pairs captured with the Sony IMX586 Quad Bayer mobile sensor and a professional 102MP medium format FujiFilm GFX100 camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to reconstruct high-quality 5MP RGB image from raw data on both platforms under 100 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
Figures & tables
Figure 1: A sample set of images from the collected dataset. From left to right: the original RAW image visualized with Photoshop’s built-in raw image processing engine, RGB image obtained with MediaTek’s built-in ISP system, and the target Fujifilm photo.
Figure 2: Loading and running custom TensorFlow Lite models with AI Benchmark application. The currently supported acceleration options include Qualcomm QNN, Hexagon NN, MediaTek Neuron, TFLite GPU, Android NNAPI and ARM NN delegates as well as CPU inference (LiteRT / XNNPACK backends). The latest app version can be downloaded at https://ai-benchmark.com/download
Team
Author
Framework
Model Size,
PSNR ↑
SSIM ↑
MOS ↑
Snapdragon 8 Elite Gen 5
Dimensity 9500
Avg. GPU
Final Score
KB
GPU, ms ↓
NPU, ms ↓
GPU, ms ↓
NPU, ms ↓
Runtime, ms ↓
MiAlgo
qyx596
PyTorch / TensorFlow
17.4
24.19
0.8587
4.5
16.6
44.1
45.4
20
27.5
96.9
AVC2
zhangyongrui
PyTorch
17.3
24.18
0.8582
4.5
59.4
40
111
Failed
81.2
32.4
UAIC_ISP
AndreiArhire
PyTorch
242
24
0.8625
4.8
727
Failed
1032
Failed
866.2
3.6
NAF
destiny
TensorFlow
75.3
23.69
0.854
4.1
227
731
270
Failed
247.6
3.1
MFI
1514288815
PyTorch
94
23.76
0.8564
4.2
893
365
1356
Failed
1100.4
0.88
Table 1: Mobile AI 2026 Learned Smartphone ISP challenge results and final rankings. During the runtime measurements, the models were processing photos of resolution 1920 × 2560 pixels on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 SoCs. Team MiAlgo is the challenge winner.
Figure 3: LKSNet architecture proposed by team MiAlgo
Figure 4: Network architecture proposed by team AVC2
Figure 5: Deep learning architecture proposed by team UAIC_ISP
Figure 6: NAF-Enhanced Smallnet model (top) and the NAFBlock architecture (bottom) proposed by team NAF
Figure 7: Multi-level feature interaction model presented by team MFI
Image reconstruction recovers images, volumes, or scenes from incomplete, noisy, indirect, or compressed measurements using physical models and learned priors.
Image denoising is a fundamental problem in mobile photography. Despite a large number of solutions proposed for this task, the majority of them are trained on synthetically produced noisy images, and are additionally too computationally heavy for processing full-resolution images on mobile devices. This creates a need for efficient deep learning-based models that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can denoise Full HD resolution photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale dataset consisting of noisy-clean image pairs captured in the wild. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to perform high-quality image denoising under 100 milliseconds on both platforms while reaching a PSNR score of over 37 dB. A comprehensive description of the models developed in the challenge is provided in this paper.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte +17
On-device RGB photo enhancement is a popular task that is needed for quality improvement of photos captured with mobile devices as well as for retouching of images acquired through other sources. This creates a need for efficient deep learning models for this problem that are not only performant but can also be deployed on constrained mobile hardware. In this Mobile AI challenge, we address this problem and propose participants to design fast solutions that can perform comprehensive enhancement of RGB photos while running on popular smartphone GPUs from Qualcomm and Arm. For this, the participants were provided with a large-scale DPED dataset consisting of RGB image pairs captured with an old iPhone 3GS smartphone and a professional Canon 70D DSLR camera. The runtime of all models was evaluated on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 chipsets with the Adreno and Mali GPUs, respectively. Top solutions proposed in this challenge are able to enhance Full HD resolution RGB images on both platforms under 300 milliseconds. A comprehensive description of the models developed in the challenge is provided in this paper.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte +21
Image super-resolution is widely used on mobile devices for upscaling various types of image data. This creates a need for efficient deep learning-based models that are not only performant but can also be deployed on neural processing units (NPUs) present in the majority of mobile and IoT chipsets. In this Mobile AI challenge, we address this problem and propose the participants to design fast solutions that can upsample images from Full HD to 4K resolution while running on popular mobile NPUs from Qualcomm and MediaTek. For this, the participants were provided with the DIV2K dataset and trained models to do an efficient 3X image upscaling. The competition had two tracks: in the first track, the models had to be fully quantized (INT8), and the runtime of all models was evaluated on the Qualcomm Snapdragon 8 Elite Gen 5 NPU. In the second track, the participants were developing floating-point solutions that were evaluated on the MediaTek Dimensity 9500 NPU. Top solutions proposed in this challenge are able to reconstruct 4K images under 5 milliseconds while reaching a PSNR score of 30 dB. A comprehensive description of the models developed in the challenge is provided in this paper.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte +43