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.
Figures & tables
Figure 1: Sample crops from the original and denoised images from the collected dataset. Best zoomed on screen.
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 ↑
Snapdragon 8 Elite Gen 5
Dimensity 9500
Avg. GPU
Final Score
KB
GPU, ms ↓
NPU, ms ↓
GPU, ms ↓
NPU, ms ↓
Runtime, ms ↓
TLG
perpetuity
PyTorch / Keras
194
37.31
0.9129
28
46
50.7
18.7
38
101.1
Fanis
nikolasent
PyTorch
469
37.48
0.912
48.1
64.9
112
Failed
73
66.6
TeamPAK
faraz2322
PyTorch
7885
37.58
0.9098
127
46.1
138
34
132
42.3
Z6
rlghksdbs
PyTorch
97.3
36.96
0.9001
69.3
51.6
115
58.1
89
26.6
IVCL
yoonsuk
PyTorch
448
37.28
0.911
1961
552
720
Failed
1188
3.1
Table 1: Mobile AI 2026 Image Denoising challenge results and final rankings. During the runtime measurements, the models were performing denoising images of resolution 1920 × 1088 pixels on the Snapdragon 8 Elite Gen 5 and Dimensity 9500 SoCs. Team TLG is the challenge winner.
Figure 3: DenoiseUnet architecture proposed by team TLG
Figure 4: FastSHADE [ 19 ] architecture proposed by team Fanis
Figure 5: Lightweight student architecture proposed by team TeamPAK
Figure 6: AGDNet architecture proposed by team Z6
Figure 7: CSPID architecture proposed by team IVCL
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
While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibility and memory-access overhead. We propose an NPU-aware hardware-algorithm co-design approach for real-world image denoising on mobile NPUs. Our approach employs a high-capacity teacher to supervise a lightweight student network specifically designed to leverage the tiled-memory architectures of modern mobile SoCs. By prioritizing NPU-native primitives -- standard 3x3 convolutions, ReLU activations, and nearest-neighbor upsampling -- and employing a progressive context expansion strategy (up to 1024x1024 crops), the model achieves 37.66 dB PSNR / 0.9278 SSIM on the validation benchmark and 37.58 dB PSNR / 0.9098 SSIM on the held-out test benchmark at full resolution (2432x3200) in the Mobile AI 2026 challenge. Following the official challenge rules, the inference runtime is measured under a standardized Full HD (1088x1920) protocol, where it runs in 34.0 ms on the MediaTek Dimensity 9500 and 46.1 ms on the Qualcomm Snapdragon 8 Elite NPU. We further reveal an "Inference Inversion" effect, where strict adherence to NPU-compatible operations enables dedicated NPU execution up to 3.88x faster than the integrated mobile GPU. The 1.96M-parameter student recovers 99.8% of the teacher's restoration quality via high-alpha knowledge distillation (alpha = 0.9), achieving a 21.2x parameter reduction while closing the PSNR gap from 1.63 dB to only 0.05 dB. These results establish hardware-aware distillation as an effective strategy for unifying high-fidelity denoising with practical deployment across diverse mobile NPU architectures. The proposed lightweight student model (LiteDenoiseNet) and its training statistics are provided in the NN Dataset, available at https://github.com/ABrain-One/NN-Dataset.
Faraz Kayani, Sarmad Kayani, Asad Ahmed +2
Computer Vision Lab, CAIDAS & IFI, University of Würzburg, Germany
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.
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte +19