The paper introduces UAR-Net, a weather‑specific all‑in‑one restoration framework that uses a gated transformer and balanced multi‑scale skip connections to handle spatially heterogeneous weather degradations. It incorporates Gated Dual‑scale Transformer Blocks for selective global and local modeling, a Progressive Balanced Multi‑scale Skip Connection for feature integration, and an Uncertainty‑Aware Refinement Head that removes artifacts, enhances details, and estimates predictive uncertainty. The network is trained with a Brightness‑Aware Energy Loss to promote accurate reconstruction and well‑calibrated uncertainty, achieving state‑of‑the‑art results on multiple adverse‑weather benchmarks.
By Zheke Jin, Yuning Cui, Tianle Jin, Alois Knoll, Hu Cao
The paper introduces TSGPD-IR, a network that disentangles weather-induced artifacts from true thermal signals in infrared images. It uses weather semantics and regional degradation severity to generate adaptive prompts, estimate severity without manual labels, and select appropriate expert modules for restoration. This approach aims to reduce artifacts and preserve weak thermal details across varying weather conditions.
By Xinyao Wang, Lijun He, Zhihan Ren, Fan Li
Remote sensing images acquired by unmanned aerial vehicles (UAVs) and satellites are often degraded by adverse weather, illumination variation, and imaging artifacts, which may co-occur and jointly induce global distribution shifts and local structural corruption. Although All-in-One image restoration offers an appealing unified alternative to task-specific pipelines, existing methods still suffer from weak or implicit degradation cues and parameter redundancy caused by full-rank multi-expert designs with overlapping restoration behaviors.
The paper introduces PGL-Net, a lightweight physics-inspired network for real‑world single image dehazing. It decouples the task into global distribution rectification and local structural refinement, using a Physics‑Inspired Affine Fusion module for global alignment and a Degradation‑Aware Modulation block for adaptive detail restoration. Experiments show that PGL‑Net, especially its Tiny variant, outperforms recent state‑of‑the‑art methods in PSNR and downstream object detection while reducing inference latency by over tenfold.
By Yifei Qu, Ru Li, Junjie Chen, Jinyuan Wu
arXiv:2609.16578v1 Announce Type: new
Abstract: The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing me...
By Hu Gao, Lizhuang Ma, Yulong Chen
arXiv:2605. 13258v2 Announce Type: replace-cross Abstract: In this work, we present our winning solution for the 8th UG2+ Challenge (CVPR 2026) Track 1: Image Restoration under All-weather Conditions.
By Youwei Pan, Leilei Cao, Yingfang Zhu, Fengjie Zhu
The paper introduces FReSH-IR, a lightweight all-in-one weather restoration method that decomposes feature representations into high- and low-frequency components across a hierarchical encoder-decoder. By integrating spectral decomposition with Fourier-based skip connections, it captures complementary frequency information while preserving spatial detail. The approach achieves comparable restoration quality to transformer-based models while using 80% fewer parameters and operations, making it efficient for high-resolution images and constrained-resource systems.
By Paula Garrido-Mellado, Daniel Feijoo, Yuning Cui, Alvaro Garcia, Marcos V. Conde
arXiv:2608. 20263v1 Announce Type: new Abstract: We propose UHDformer++, a general Transformer-based framework to solve numerous Ultra-High-Definition (UHD) image restoration tasks.
By Cong Wang, Liyan Wang, Jinshan Pan, Wei Wang, Wenqi Ren, Jun Liu, Xiaochun Cao
MOSAIC is an object‑centric framework that adapts pretrained diffusion Transformers for image restoration by learning compact structural conditions. It organizes degraded images into structural slots capturing object‑level and layout‑level evidence, integrates these across resolutions, and retrieves recurring priors from a shared prototype memory. Injecting these representations into selected layers of a frozen diffusion Transformer via lightweight residual modulation preserves the pretrained generative prior, yielding improved remote sensing image super‑resolution performance on UCMerced, AID, and RSSCN7 datasets.
By Liuqian Wang, Hanyu Xie, Rongzhen Zhao, Qi Ming, Chunjie Ma, Wentao Chao, Yufei Gao, Chengming Liu, Lei Shi
arXiv:2609.00811v1 Announce Type: new
Abstract: Flow Matching provides an efficient generative prior for image restoration by learning continuous transport between source and data distributions. Howe...
By Jiaqi Zhang, Yiqi Wang, Hongjie Wu, Bohan Guo, Xinan Wang, Zichen Luo, Taotao Cai, Zhi Chen, Mingkai Zheng
arXiv:2610.27793v1 Announce Type: cross
Abstract: Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations i...
By Amirpasha Mozaffari, Marina Casta\~no, Stefano Materia, Joan Vedr\'i, Jordi Varela-Agrelo, Dario Garcia-Gasulla, Etienne Tourigny, Mario Acosta, Amanda Duarte
arXiv:2608.29220v1 Announce Type: new
Abstract: Multimodal image fusion (MMIF) aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality while el...
By Haozhen Wei, Chengjun Jiang, Yutong Guo, Xinrui Ju, Xingyuan Li, Xiang Chen, Jinyuan Liu