paper-with-me

홈 › Papers

Breaking the Multi-Enhancement Bottleneck: Domain-Consistent Quality Enhancement for Compressed Images

2025-06-17 · Qunliang Xing, Mai Xu, Jing Yang, Shengxi Li

Quality enhancement methods have been widely integrated into visual communication pipelines to mitigate artifacts in compressed images. Ideally, these quality enhancement methods should perform robustly when applied to images that have already undergone prior enhancement during transmission. We refer to this scenario as multi-enhancement, which generalizes the well-known multi-generation scenario of image compression. Unfortunately, current quality enhancement methods suffer from severe degradation when applied in multi-enhancement. To address this challenge, we propose a novel adaptation method that transforms existing quality enhancement models into domain-consistent ones. Specifically, our method enhances a low-quality compressed image into a high-quality image within the natural domain during the first enhancement, and ensures that subsequent enhancements preserve this quality without further degradation. Extensive experiments validate the effectiveness of our method and show that various existing models can be successfully adapted to maintain both fidelity and perceptual quality in multi-enhancement scenarios.

📄 PDF Abstract BibTeX arXiv:2506.14152

Code (0)

등록된 구현이 없습니다.

Tasks

Image Compression

Similar Papers 제목 키워드 기반

Clique Analysis and Bypassing in Continuous-Time Conflict-Based Search

2023-12-26 · Thayne T. Walker, Nathan R. Sturtevant, Ariel Felner

While the study of unit-cost Multi-Agent Pathfinding (MAPF) problems has been popular, many real-world problems require continuous time and costs due to various movement models. In this context, this paper studies symmet…

LEAD: Breaking the No-Recovery Bottleneck in Long-Horizon Reasoning

2026-03-06 · Denys Pushkin, Emmanuel Abbe arxiv

Long-horizon execution in Large Language Models (LLMs) remains unstable even when high-level strategies are provided. Evaluating on controlled algorithmic puzzles, we demonstrate that while decomposition is essential for…

DNF: Decouple and Feedback Network for Seeing in the Dark

2023-01-01 · CVPR 2023 1 · Xin Jin, Ling-Hao Han, Zhen Li, Chun-Le Guo 외

The exclusive properties of RAW data have shown great potential for low-light image enhancement. Nevertheless, the performance is bottlenecked by the inherent limitations of existing architectures in both single-stag…

Image EnhancementLow-Light Image Enhancement

Self-supervised Domain Adaptation for Breaking the Limits of Low-quality Fundus Image Quality Enhancement

2023-01-17 · Qingshan Hou, Peng Cao, Jiaqi Wang, Xiaoli Liu 외

Retinal fundus images have been applied for the diagnosis and screening of eye diseases, such as Diabetic Retinopathy (DR) or Diabetic Macular Edema (DME). However, both low-quality fundus images and style inconsistency …

Domain AdaptationImage Enhancement

Sigsoftmax: Reanalysis of the Softmax Bottleneck

2018-05-28 · NeurIPS 2018 12 · Sekitoshi Kanai, Yasuhiro Fujiwara, Yuki Yamanaka, Shuichi Adachi

Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational cap…

Language ModelingLanguage Modelling