The paper introduces Restoring without Forgetting (RwF), a continual learning framework for image restoration that handles multiple degradations sequentially without accessing prior data. RwF trains a lightweight adapter for each new degradation, uses an unsupervised routing mechanism to select the correct restoration path, and achieves significant PSNR gains over fine‑tuning on five benchmark degradation domains. The method also demonstrates strong transfer performance on eleven real‑degradation datasets with high routing accuracy.
By Alif Ashrafee, Bartosz Krawczyk
arXiv:2606. 28112v1 Announce Type: cross Abstract: Degradation-aware prompts, conditions, and latent priors are increasingly used in image restoration, yet they are usually judged by a single endpoint: whether the restored image obtains higher PSNR.
By Xinrui Wu, Lichen Huang
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.
arXiv:2608. 09482v1 Announce Type: cross Abstract: All-in-one image restoration is a unified low-level vision task that aims to effectively recover high-quality images from inputs degraded by various types and levels of corruption using a single model.
By Chunxiao Liu, Wei Liu, Anbin Xiong, Erli Meng
arXiv:2608. 20141v1 Announce Type: new Abstract: All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model.
By Zhaokun He, Kangbiao Shi, Axi Niu, Jian Jin, Peng Wu, Wei Dong, Qingsen Yan
arXiv:2608. 16010v1 Announce Type: new Abstract: Model compression is critical for deploying networks on resource-constrained edge devices.
By Zhaocen Liu, Satvik Praveen, Yi Sheng
arXiv:2605. 20247v2 Announce Type: replace-cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).
By Yang Liu, Toan Nguyen, Flora D. Salim
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
Loop‑Mamba is a lightweight, loop‑based state‑space framework designed for restoring old photographs that suffer from multiple degradations such as scratches, cracks, fading, blur, noise, and missing regions. It models restoration as progressive state evolution, using a Semantic‑Guided Degradation Estimator to predict local degradation maps and global scores, and a Shared Structural Memory Mamba to maintain a persistent restoration state across iterations. The method employs first‑order state recursion and a multi‑directional scanning strategy to reduce gradient dilution and computational overhead, and introduces the Old Photo Damage Recovery Score (ODRS) to evaluate both degradation recovery and structural reconstruction, achieving superior performance on the SynOld benchmark.
By Runci Bai, Yucheng Xin, Pu Wang, Yongcong Wang, Chen Wu, Dianjie Lu, Guijuan Zhang, Pengwen Dai, Guangwei Gao, Siyuan Yao, Zhuoran Zheng
arXiv:2510. 21978v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models.
By Hoang Phan, Xianjun Yang, Yuanshun Yao, Jingyu Zhang, Shengjie Bi, Xiaocheng Tang, Madian Khabsa, Lijuan Liu, Deren Lei
RegCL is a non‑replay continual learning framework that adapts the Segment Anything Model (SAM) for visual grounding across evolving multi‑sensorial media domains. It consolidates domain‑specific segmentation knowledge into a single lightweight SAM adapter by incrementally merging LoRA‑style AugModules and preserving compact historical feature statistics. Experiments on five heterogeneous datasets demonstrate that RegCL retains performance while adapting to new domains, outperforming other non‑replay continual learning and merging baselines.
By Yuan-Chen Shu, Zhiwei Lin, Xiaoyu Zhou, Yongtao Wang
arXiv:2606. 07500v1 Announce Type: cross Abstract: Continual learning in Large Language Models (LLMs) is hindered by the plasticity-stability dilemma, where acquiring new capabilities often leads to catastrophic forgetting of previous knowledge.
By Fatema Siddika, Md Anwar Hossen, Tanwi Mallick, Ali Jannesari