中文
相关论文

相关论文: PASDiff: Physics-Aware Semantic Guidance for Joint…

200 篇论文

Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical…

计算机视觉与模式识别 · 计算机科学 2025-10-15 Wenjie Li , Xiangyi Wang , Heng Guo , Guangwei Gao , Zhanyu Ma

With the increasing deployment of facial image data across a wide range of applications, efficient compression tailored to facial semantics has become critical for both storage and transmission. While recent learning-based face image…

计算机视觉与模式识别 · 计算机科学 2025-11-12 Yimin Zhou , Yichong Xia , Bin Chen , Mingyao Hong , Jiawei Li , Zhi Wang , Yaowei Wang

Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE:…

计算机视觉与模式识别 · 计算机科学 2024-07-24 Yunlong Lin , Tian Ye , Sixiang Chen , Zhenqi Fu , Yingying Wang , Wenhao Chai , Zhaohu Xing , Lei Zhu , Xinghao Ding

We introduce a novel approach to single-view face relighting in the wild, addressing challenges such as global illumination and cast shadows. A common scheme in recent methods involves intrinsically decomposing an input image into 3D shape,…

计算机视觉与模式识别 · 计算机科学 2026-05-13 Puntawat Ponglertnapakorn , Nontawat Tritrong , Supasorn Suwajanakorn

Exploiting pre-trained diffusion models for restoration has recently become a favored alternative to the traditional task-specific training approach. Previous works have achieved noteworthy success by limiting the solution space using…

计算机视觉与模式识别 · 计算机科学 2023-09-20 Peiqing Yang , Shangchen Zhou , Qingyi Tao , Chen Change Loy

Images captured in challenging environments--such as nighttime, smoke, rainy weather, and underwater--often suffer from significant degradation, resulting in a substantial loss of visual quality. The effective restoration of these degraded…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Wenfeng Huang , Guoan Xu , Wenjing Jia , Stuart Perry , Guangwei Gao

The ability to create high-quality 3D faces from a single image has become increasingly important with wide applications in video conferencing, AR/VR, and advanced video editing in movie industries. In this paper, we propose Face Diffusion…

计算机视觉与模式识别 · 计算机科学 2023-12-05 Hao Zhang , Yanbo Xu , Tianyuan Dai , Yu-Wing Tai , Chi-Keung Tang

Recovering noise-covered details from low-light images is challenging, and the results given by previous methods leave room for improvement. Recent diffusion models show realistic and detailed image generation through a sequence of…

计算机视觉与模式识别 · 计算机科学 2023-05-18 Dewei Zhou , Zongxin Yang , Yi Yang

Face fill-light enhancement (FFE) brightens underexposed faces by adding virtual fill light while keeping the original scene illumination and background unchanged. Most face relighting methods aim to reshape overall lighting, which can…

计算机视觉与模式识别 · 计算机科学 2026-02-05 Jue Gong , Zihan Zhou , Jingkai Wang , Xiaohong Liu , Yulun Zhang , Xiaokang Yang

Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input. To this…

计算机视觉与模式识别 · 计算机科学 2024-12-02 Junyang Chen , Jinshan Pan , Jiangxin Dong

In this paper, we rethink the low-light image enhancement task and propose a physically explainable and generative diffusion model for low-light image enhancement, termed as Diff-Retinex. We aim to integrate the advantages of the physical…

计算机视觉与模式识别 · 计算机科学 2023-08-28 Xunpeng Yi , Han Xu , Hao Zhang , Linfeng Tang , Jiayi Ma

Underwater images are severely degraded by wavelength-dependent light absorption and scattering, resulting in color distortion, low contrast, and loss of fine details that hinder vision-based underwater applications. To address these…

计算机视觉与模式识别 · 计算机科学 2025-12-18 Afrah Shaahid , Muzammil Behzad

Image decomposition offers deep insights into the imaging factors of visual data and significantly enhances various advanced computer vision tasks. In this work, we introduce a novel approach to low-light image enhancement based on…

计算机视觉与模式识别 · 计算机科学 2025-04-17 Xingxing Yang , Jie Chen , Zaifeng Yang

JPEG, as a widely used image compression standard, often introduces severe visual artifacts when achieving high compression ratios. Although existing deep learning-based restoration methods have made considerable progress, they often…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Tingyu Yang , Jue Gong , Jinpei Guo , Wenbo Li , Yong Guo , Yulun Zhang

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

Diffusion-based generative models have shown promise in synthesizing histopathology images to address data scarcity caused by privacy constraints. Diagnostic text reports provide high-level semantic descriptions, and masks offer…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Mahesh Bhosale , Abdul Wasi , Yuanhao Zhai , Yunjie Tian , Samuel Border , Nan Xi , Pinaki Sarder , Junsong Yuan , David Doermann , Xuan Gong

Despite promising progress in face swapping task, realistic swapped images remain elusive, often marred by artifacts, particularly in scenarios involving high pose variation, color differences, and occlusion. To address these issues, we…

计算机视觉与模式识别 · 计算机科学 2024-09-12 Sanoojan Baliah , Qinliang Lin , Shengcai Liao , Xiaodan Liang , Muhammad Haris Khan

We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps.…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Peter Kocsis , Vincent Sitzmann , Matthias Nießner

Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in degraded images. Those…

计算机视觉与模式识别 · 计算机科学 2025-07-04 Jaewon Min , Jin Hyeon Kim , Paul Hyunbin Cho , Jaeeun Lee , Jihye Park , Minkyu Park , Sangpil Kim , Hyunhee Park , Seungryong Kim

Adverse Weather Image Restoration (AWIR) is a highly challenging task due to the unpredictable and dynamic nature of weather-related degradations. Traditional task-specific methods often fail to generalize to unseen or complex degradation…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Wenxuan Fang , Jili Fan , Chao Wang , Xiantao Hu , Jiangwei Weng , Ying Tai , Jian Yang , Jun Li
‹ 上一页 1 2 3 10 下一页 ›