paper-with-me

Papers

Sparsity-Aware Optimal Transport for Unsupervised Restoration Learning

2023-04-29 · Fei Wen, Wei Wang, Wenxian Yu

Recent studies show that, without any prior model, the unsupervised restoration learning problem can be optimally formulated as an optimal transport (OT) problem, which has shown promising performance on denoising tasks to approach the performance of supervised methods. However, it still significantly lags behind state-of-the-art supervised methods on complex restoration tasks such as super-resolution, deraining, and dehazing. In this paper, we exploit the sparsity of degradation in the OT framework to significantly boost its performance on these tasks. First, we disclose an observation that the degradation in these tasks is quite sparse in the frequency domain, and then propose a sparsity-aware optimal transport (SOT) criterion for unsupervised restoration learning. Further, we provide an analytic example to illustrate that exploiting the sparsity helps to reduce the ambiguity in finding an inverse map for restoration. Experiments on real-world super-resolution, deraining, and dehazing demonstrate that SOT can improve the PSNR of OT by about 2.6 dB, 2.7 dB and 1.3 dB, respectively, while achieving the best perception scores among the compared supervised and unsupervised methods. Particularly, on the three tasks, SOT significantly outperforms existing unsupervised methods and approaches the performance of state-of-the-art supervised methods.

📄 PDF Abstract BibTeX arXiv:2305.00273

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingRain RemovalSuper-Resolution

Similar Papers 제목 키워드 기반

Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

2024-11-03 · Xiaole Tang, Xiang Gu, Xiaoyi He, Xin Hu 외

All-in-one image restoration has emerged as a practical and promising low-level vision task for real-world applications. In this context, the key issue lies in how to deal with different types of degraded images simultan…

5-Degradation Blind All-in-One Image RestorationBlind All-in-One Image RestorationImage RestorationUnified Image Restoration

Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration

2024-05-05 · Xiaole Tang, Xin Hu, Xiang Gu, Jian Sun

Deep learning-based image restoration methods generally struggle with faithfully preserving the structures of the original image. In this work, we propose a novel Residual-Conditioned Optimal Transport (RCOT) approach, w…

Color Image DenoisingImage RestorationImage Super-Resolution

Unifying Heterogeneous Degradations: Uncertainty-Aware Diffusion Bridge Model for All-in-One Image Restoration

2026-01-29 · Luwei Tu, Jiawei Wu, Xing Luo, Zhi Jin arxiv

All-in-One Image Restoration (AiOIR) faces the fundamental challenge in reconciling conflicting optimization objectives across heterogeneous degradations. Existing methods are often constrained by coarse-grained control …

Image Restoration

COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimation

2026-02-28 · Yuchen Che, Jingtu Wu, Hao Zheng, Asako Kanezaki arxiv

Estimating the 6DoF pose of a novel object with a single reference view is challenging due to occlusions, view-point changes, and outliers. A core difficulty lies in finding robust cross-view correspondences, as existing…

Pose Estimation

OMH: Structured Sparsity via Optimally Matched Hierarchy for Unsupervised Semantic Segmentation

2024-03-11 · Baran Ozaydin, Tong Zhang, Deblina Bhattacharjee, Sabine Süsstrunk 외

Unsupervised Semantic Segmentation (USS) involves segmenting images without relying on predefined labels, aiming to alleviate the burden of extensive human labeling. Existing methods utilize features generated by self-su…

ClusteringSemantic SegmentationUnsupervised Semantic Segmentation