中文
相关论文

相关论文: ZeroIDIR: Zero-Reference Illumination Degradation …

200 篇论文

Diffusion model-based low-light image enhancement methods rely heavily on paired training data, leading to limited extensive application. Meanwhile, existing unsupervised methods lack effective bridging capabilities for unknown degradation.…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Jinhong He , Minglong Xue , Aoxiang Ning , Chengyun Song

We present DiffIR2VR-Zero, a zero-shot framework that enables any pre-trained image restoration diffusion model to perform high-quality video restoration without additional training. While image diffusion models have shown remarkable…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Chang-Han Yeh , Hau-Shiang Shiu , Chin-Yang Lin , Zhixiang Wang , Chi-Wei Hsiao , Ting-Hsuan Chen , Yu-Lun Liu

Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre-trained features to enhance degradation expression, while…

计算机视觉与模式识别 · 计算机科学 2026-05-26 XiaoWan Hu , Jing Yang , HeNan Liu , HuaQiu Li , Mai Xu

Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Chunming He , Chengyu Fang , Yulun Zhang , Tian Ye , Kai Li , Longxiang Tang , Zhenhua Guo , Xiu Li , Sina Farsiu

Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for…

计算机视觉与模式识别 · 计算机科学 2022-12-08 Yinhuai Wang , Jiwen Yu , Jian Zhang

We present AutoDIR, an innovative all-in-one image restoration system incorporating latent diffusion. AutoDIR excels in its ability to automatically identify and restore images suffering from a range of unknown degradations. AutoDIR offers…

计算机视觉与模式识别 · 计算机科学 2024-05-29 Yitong Jiang , Zhaoyang Zhang , Tianfan Xue , Jinwei Gu

Diffusion models have achieved remarkable success in imaging inverse problems owing to their powerful generative capabilities. However, existing approaches typically rely on models trained for specific degradation types, limiting their…

计算机视觉与模式识别 · 计算机科学 2025-06-17 Zhen Wang , Hongyi Liu , Zhihui Wei

Low-light image enhancement aims to improve the visibility of degraded images to better align with human visual perception. While diffusion-based methods have shown promising performance due to their strong generative capabilities. However,…

计算机视觉与模式识别 · 计算机科学 2025-07-25 Jinhong He , Minglong Xue , Zhipu Liu , Mingliang Zhou , Aoxiang Ning , Palaiahnakote Shivakumara

Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a…

计算机视觉与模式识别 · 计算机科学 2025-09-09 Shady Abu-Hussein , Tom Tirer , Raja Giryes

In nighttime circumstances, it is challenging for individuals and machines to perceive their surroundings. While prevailing image restoration methods adeptly handle singular forms of degradation, they falter when confronted with intricate…

计算机视觉与模式识别 · 计算机科学 2026-05-15 Yifan Chen , Fei Yin , Chunle Guo , Chongyi Li , Yujiu Yang

Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc. However, due to the inherent complexity and non-uniqueness of…

计算机视觉与模式识别 · 计算机科学 2024-07-08 Yuhong Zhang , Hengsheng Zhang , Xinning Chai , Zhengxue Cheng , Rong Xie , Li Song , Wenjun Zhang

Video restoration aims to reconstruct high quality video sequences from low quality inputs, addressing tasks such as super resolution, denoising, and deblurring. Traditional regression based methods often produce unrealistic details and…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Sicheng Gao , Nancy Mehta , Zongwei Wu , Radu Timofte

Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement. However, directly applying them to video restoration and enhancement results in severe…

计算机视觉与模式识别 · 计算机科学 2025-02-04 Cong Cao , Huanjing Yue , Xin Liu , Jingyu Yang

Zero-shot image restoration (IR) methods based on pretrained diffusion models have recently achieved significant success. These methods typically require at least a parametric form of the degradation model. However, in real-world scenarios,…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Hamadi Chihaoui , Paolo Favaro

Two of the main challenges of image restoration in real-world scenarios are the accurate characterization of an image prior and the precise modeling of the image degradation operator. Pre-trained diffusion models have been very successfully…

计算机视觉与模式识别 · 计算机科学 2025-03-28 Hamadi Chihaoui , Paolo Favaro

Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network. However, different from image synthesis, image restoration (IR) has a strong constraint to…

计算机视觉与模式识别 · 计算机科学 2023-08-17 Bin Xia , Yulun Zhang , Shiyin Wang , Yitong Wang , Xinglong Wu , Yapeng Tian , Wenming Yang , Luc Van Gool

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…

计算机视觉与模式识别 · 计算机科学 2023-08-16 Yufei Wang , Yi Yu , Wenhan Yang , Lanqing Guo , Lap-Pui Chau , Alex C. Kot , Bihan Wen

Hyperspectral image (HSI) restoration aims at recovering clean images from degraded observations and plays a vital role in downstream tasks. Existing model-based methods have limitations in accurately modeling the complex image…

计算机视觉与模式识别 · 计算机科学 2024-02-27 Li Pang , Xiangyu Rui , Long Cui , Hongzhong Wang , Deyu Meng , Xiangyong Cao

Image Restoration (IR) methods based on a pre-trained diffusion model have demonstrated state-of-the-art performance. However, they have two fundamental limitations: 1) they often assume that the degradation operator is completely known and…

计算机视觉与模式识别 · 计算机科学 2024-11-06 Hamadi Chihaoui , Abdelhak Lemkhenter , Paolo Favaro

We present DiffBIR, a general restoration pipeline that could handle different blind image restoration tasks in a unified framework. DiffBIR decouples blind image restoration problem into two stages: 1) degradation removal: removing…

计算机视觉与模式识别 · 计算机科学 2024-04-15 Xinqi Lin , Jingwen He , Ziyan Chen , Zhaoyang Lyu , Bo Dai , Fanghua Yu , Wanli Ouyang , Yu Qiao , Chao Dong
‹ 上一页 1 2 3 10 下一页 ›