paper-with-me

Papers

Vision-Language Gradient Descent-driven All-in-One Deep Unfolding Networks

2025-03-21 · CVPR 2025 1 · Haijin Zeng, Xiangming Wang, Yongyong Chen, Jingyong Su, Jie Liu

Dynamic image degradations, including noise, blur and lighting inconsistencies, pose significant challenges in image restoration, often due to sensor limitations or adverse environmental conditions. Existing Deep Unfolding Networks (DUNs) offer stable restoration performance but require manual selection of degradation matrices for each degradation type, limiting their adaptability across diverse scenarios. To address this issue, we propose the Vision-Language-guided Unfolding Network (VLU-Net), a unified DUN framework for handling multiple degradation types simultaneously. VLU-Net leverages a Vision-Language Model (VLM) refined on degraded image-text pairs to align image features with degradation descriptions, selecting the appropriate transform for target degradation. By integrating an automatic VLM-based gradient estimation strategy into the Proximal Gradient Descent (PGD) algorithm, VLU-Net effectively tackles complex multi-degradation restoration tasks while maintaining interpretability. Furthermore, we design a hierarchical feature unfolding structure to enhance VLU-Net framework, efficiently synthesizing degradation patterns across various levels. VLU-Net is the first all-in-one DUN framework and outperforms current leading one-by-one and all-in-one end-to-end methods by 3.74 dB on the SOTS dehazing dataset and 1.70 dB on the Rain100L deraining dataset.

📄 PDF Abstract BibTeX arXiv:2503.16930

Code (0)

등록된 구현이 없습니다.

Tasks

AllImage RestorationRain Removal

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

DDPG-Driven Deep-Unfolding with Adaptive Depth for Channel Estimation with Sparse Bayesian Learning

2022-01-20 · Qiyu Hu, Shuhan Shi, Yunlong Cai, Guanding Yu

Deep-unfolding neural networks (NNs) have received great attention since they achieve satisfactory performance with relatively low complexity. Typically, these deep-unfolding NNs are restricted to a fixed-depth for all i…

Deep Generalized Unfolding Networks for Image Restoration

2022-04-28 · CVPR 2022 1 · Chong Mou, Qian Wang, Jian Zhang

Deep neural networks (DNN) have achieved great success in image restoration. However, most DNN methods are designed as a black box, lacking transparency and interpretability. Although some methods are proposed to combine…

Image Restoration

Convergence Acceleration of Markov Chain Monte Carlo-based Gradient Descent by Deep Unfolding

2024-02-21 · Ryo Hagiwara, Satoshi Takabe

This study proposes a trainable sampling-based solver for combinatorial optimization problems (COPs) using a deep-learning technique called deep unfolding. The proposed solver is based on the Ohzeki method that combines …

Combinatorial Optimization

Proximal Gradient Descent Unfolding Dense-spatial Spectral-attention Transformer for Compressive Spectral Imaging

2023-12-25 · Ziyan Chen, Jing Cheng

The Coded Aperture Snapshot Spectral Compressive Imaging (CASSI) system modulates three-dimensional hyperspectral images into two-dimensional compressed images in a single exposure. Subsequently, three-dimensional hypers…

GPU

Beyond Single Solution: Multi-Hypothesis Collaborative Deep Unfolding Network for Image Compressive Sensing

2026-06-02 · Wenxue Cui, Hualin Li, Yuhang Qin, Yifu Xu 외 arxiv

Recent deep unfolding networks (DUNs) have advanced Compressive Sensing (CS) by effectively integrating iterative optimization with deep learning architectures. However, most CS approaches predominantly confine their inf…

Compressive Sensing