AI RESEARCH

Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions

arXiv CS.AI

ArXi:2605.24621v1 Announce Type: cross Scattering transforms achieve Lipschitz stability and translation invariance, but dense prediction tasks require preserving spatial structure lost in global averaging. We propose Phase-Aware Scattering Encoder-Decoder, which res this information by explicitly preserving phase in skip connections. On image denoising (BSD68), breaking translation invariance improves PSNR by $+2.17$~dB; phase preservation adds $+1.03$~dB. A novel spatial shuffling ablation ($-1.26$~dB penalty) nstrates phase encodes location-dependent structure.