Reproduce “WaFIR: Wavelet-Fourier Mixture-of-Experts with Subband-Adaptive Routing for Blind All-in-One Image Restoration” 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
Trong Nhan Nguyen, Vu Hoang Minh Doan, Thanh Dat Le, Truong Tien Vo, Thi Thu Ha Vu, Tan Hung Vo, Jaeyeop Choi, Junghwan Oh and 1 more
WaFIR routes intermediate image features from four Haar-wavelet subbands to specialists, using each band’s Fourier descriptor alongside PromptIR’s learned prompt context. It requires no degradation label at inference. Under a unified protocol, it reports a mean PSNR of 32.54 dB, 0.48 dB above PromptIR across five test conditions. However, AdaIR’s mean is higher, and WaFIR trails PromptIR on dehazing.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.