Search Results for author:
Found 3 papers, 2 papers with code
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration
More crucially, we design the transport map for restoration as a two-pass DA-RCOT map, in which the transport residual is computed in the first pass and then encoded as multi-scale residual embeddings to condition the second-pass restoration.
Ranked #1 on
Unified Image Restoration
on BSD68 sigma25
5-Degradation Blind All-in-One Image Restoration
Unified Image Restoration
Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration
In this work, we propose a novel Residual-Conditioned Optimal Transport (RCOT) approach, which models image restoration as an optimal transport (OT) problem for both unpaired and paired settings, introducing the transport residual as a unique degradation-specific cue for both the transport cost and the transport map.
Ranked #4 on
Image Super-Resolution
on DIV2K val - 4x upscaling
Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior
To address this challenge, we suggest a dataset-free deep residual prior for the kernel induced error (termed as residual) expressed by a customized untrained deep neural network, which allows us to flexibly adapt to different blurs and images in real scenarios.
