中文
相关论文

相关论文: CANDLE: Illumination-Invariant Semantic Priors for…

200 篇论文

This paper presents a new ambient light normalization framework, DINOLight, that integrates the self-supervised model DINOv2's image understanding capability into the restoration process as a visual prior. Ambient light normalization aims…

计算机视觉与模式识别 · 计算机科学 2026-03-16 Youngjin Oh , Junhyeong Kwon , Nam Ik Cho

Adverse lighting conditions, such as cast shadows and irregular illumination, pose significant challenges to computer vision systems by degrading visibility and color fidelity. Consequently, effective shadow removal and ALN are critical for…

计算机视觉与模式识别 · 计算机科学 2026-04-17 Youngjin Oh , Junyoung Park , Junhyeong Kwon , Nam Ik Cho

Lighting normalization is a crucial but underexplored restoration task with broad applications. However, existing works often simplify this task within the context of shadow removal, limiting the light sources to one and oversimplifying the…

计算机视觉与模式识别 · 计算机科学 2024-03-28 Florin-Alexandru Vasluianu , Tim Seizinger , Zongwei Wu , Rakesh Ranjan , Radu Timofte

Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IFBlend, leverage frequency-domain priors to model illumination variations, but still…

计算机视觉与模式识别 · 计算机科学 2026-04-16 Jiatao Dai , Wei Dong , Han Zhou , Chengzhou Tang , Jun Chen

Low-light image enhancement (LLIE) has traditionally been formulated as a deterministic mapping. However, this paradigm often struggles to account for the ill-posed nature of the task, where unknown ambient conditions and sensor parameters…

计算机视觉与模式识别 · 计算机科学 2026-03-27 Hongru Han , Tingrui Guo , Liming Zhang , Yan Su , Qiwen Xu , Zhuohua Ye

Extreme exposure degrades both the 3D map reconstruction and semantic segmentation accuracy, which is particularly detrimental to tightly-coupled systems. To achieve illumination invariance, we propose a novel semantic SLAM framework with…

计算机视觉与模式识别 · 计算机科学 2025-12-01 Shouhe Zhang , Dayong Ren , Sensen Song , Yurong Qian , Zhenhong Jia

Illumination in practical scenarios is inherently complex, involving colored light sources, occlusions, and diverse material interactions that produce intricate reflectance and shading effects. However, existing methods often oversimplify…

计算机视觉与模式识别 · 计算机科学 2025-08-06 Florin-Alexandru Vasluianu , Tim Seizinger , Zongwei Wu , Radu Timofte

Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level…

计算机视觉与模式识别 · 计算机科学 2026-03-11 Junyuan Mao , Qiankun Li , Linghao Meng , Zhicheng He , Xinliang Zhou , Kun Wang , Yang Liu , Yueming Jin

Foreground-conditioned inpainting aims to seamlessly fill the background region of an image by utilizing the provided foreground subject and a text description. While existing T2I-based image inpainting methods can be applied to this task,…

计算机视觉与模式识别 · 计算机科学 2025-08-07 Guangben Lu , Yuzhen Du , Zhimin Sun , Ran Yi , Yifan Qi , Yizhe Tang , Tianyi Wang , Lizhuang Ma , Fangyuan Zou

Low-light image enhancement (LLIE) investigates how to improve illumination and produce normal-light images. The majority of existing methods improve low-light images via a global and uniform manner, without taking into account the semantic…

计算机视觉与模式识别 · 计算机科学 2023-04-17 Yuhui Wu , Chen Pan , Guoqing Wang , Yang Yang , Jiwei Wei , Chongyi Li , Heng Tao Shen

Inverse rendering is an ill-posed problem. Previous work has sought to resolve this by focussing on priors for object or scene shape or appearance. In this work, we instead focus on a prior for natural illuminations. Current methods rely on…

计算机视觉与模式识别 · 计算机科学 2023-11-17 James A. D. Gardner , Bernhard Egger , William A. P. Smith

Colorizing grayscale images offers an engaging visual experience. Existing automatic colorization methods often fail to generate satisfactory results due to incorrect semantic colors and unsaturated colors. In this work, we propose an…

计算机视觉与模式识别 · 计算机科学 2024-04-26 Han Wang , Xinning Chai , Yiwen Wang , Yuhong Zhang , Rong Xie , Li Song

Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the…

计算机视觉与模式识别 · 计算机科学 2023-09-06 Naishan Zheng , Man Zhou , Yanmeng Dong , Xiangyu Rui , Jie Huang , Chongyi Li , Feng Zhao

Near-infrared (NIR) image spectrum translation is a challenging problem with many promising applications. Existing methods struggle with the mapping ambiguity between the NIR and the RGB domains, and generalize poorly due to the limitations…

计算机视觉与模式识别 · 计算机科学 2023-08-08 Xingxing Yang , Jie Chen , Zaifeng Yang

Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images. In this paper, we respond to the intriguing learning-related question -- if leveraging…

计算机视觉与模式识别 · 计算机科学 2021-12-14 Dong Liang , Ling Li , Mingqiang Wei , Shuo Yang , Liyan Zhang , Wenhan Yang , Yun Du , Huiyu Zhou

Images captured under low-light conditions manifest poor visibility, lack contrast and color vividness. Compared to conventional approaches, deep convolutional neural networks (CNNs) perform well in enhancing images. However, being solely…

计算机视觉与模式识别 · 计算机科学 2021-01-05 Aditya Arora , Muhammad Haris , Syed Waqas Zamir , Munawar Hayat , Fahad Shahbaz Khan , Ling Shao , Ming-Hsuan Yang

Recent work has shown that the structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. This prior, known as a deep image prior (DIP), is an effective regularizer in inverse problems such as image…

计算机视觉与模式识别 · 计算机科学 2020-12-03 Pallabi Ghosh , Vibhav Vineet , Larry S. Davis , Abhinav Shrivastava , Sudipta Sinha , Neel Joshi

Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insufficient illumination often leads to low contrast, detail loss, and noise. Recent studies show that deep learning-based Retinex theory can…

计算机视觉与模式识别 · 计算机科学 2026-05-20 Ziqi Wang , Xu Zhang , Laibin Chang , Shi Chen , Jiaqi Ma , Huan Zhang

Zero-Shot Anomaly Detection (ZSAD) seeks to identify anomalies from arbitrary novel categories, offering a scalable and annotation-efficient solution. Traditionally, most ZSAD works have been based on the CLIP model, which performs anomaly…

计算机视觉与模式识别 · 计算机科学 2025-09-19 Jingyi Yuan , Jianxiong Ye , Wenkang Chen , Chenqiang Gao

Image-to-image relighting requires representations that disentangle scene properties from illumination. Recent methods rely on latent intrinsic representations but remain under-constrained and often fail on challenging materials such as…

计算机视觉与模式识别 · 计算机科学 2026-02-03 Xiaoyan Xing , Xiao Zhang , Sezer Karaoglu , Theo Gevers , Anand Bhattad
‹ 上一页 1 2 3 10 下一页 ›