Reproduce “RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andrey Ignatov, Georgy Perevozchikov, Radu Timofte, Dong Zhang, Zhao Ran, Yang Zhang, Xiaochen Li, Shichang Ju and 16 more
The authors describe DENet mapping iPhone 3GS photos toward Canon 70D references for smartphone GPUs. DaHua-IIG trains a RetinexFormer teacher to create pseudo-ground-truth targets for a pruned PLU-Net student. In the six-team challenge, it achieved the best perceptual reconstruction results, with GPU times of 23.8 and 60.4 ms; ablations do not establish which choices produced them.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.