中文
相关论文

相关论文: NLHD: A Pixel-Level Non-Local Retinex Model for Lo…

200 篇论文

Image harmonization aims to generate a more realistic appearance of foreground and background for a composite image. Existing methods perform the same harmonization process for the whole foreground. However, the implanted foreground always…

计算机视觉与模式识别 · 计算机科学 2022-05-16 Jinlong Peng , Zekun Luo , Liang Liu , Boshen Zhang , Tao Wang , Yabiao Wang , Ying Tai , Chengjie Wang , Weiyao Lin

Full 360$^\circ$ novel view synthesis under low-light conditions remains challenging. Insufficient illumination, noise amplification, and view-dependent photometric inconsistencies prevent existing methods from jointly preserving geometric…

计算机视觉与模式识别 · 计算机科学 2026-04-28 YuHao Yin , Zongji Wang , Yuanben Zhang , Biqing Li , Jiesong Bai , Junyi Liu

The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task,…

图像与视频处理 · 电气工程与系统科学 2020-05-22 Cheng Zhang , Qingsen Yan , Yu zhu , Xianjun Li , Jinqiu Sun , Yanning Zhang

Hand-held light field (LF) cameras often exhibit low spatial resolution due to the inherent trade-off between spatial and angular dimensions. Existing supervised learning-based LF spatial super-resolution (SR) methods, which rely on…

图像与视频处理 · 电气工程与系统科学 2025-12-09 Jianxin Lei , Dongze Wu , Chengcai Xu , Hongcheng Gu , Guangquan Zhou , Junhui Hou , Ping Zhou

Image degradation caused by complex lighting conditions such as low-light and backlit scenarios is commonly encountered in real-world environments, significantly affecting image quality and downstream vision tasks. Most existing methods…

计算机视觉与模式识别 · 计算机科学 2025-08-20 Ziang Wang , Xiaoqin Wang , Dingyi Wang , Qiang Li , Shushan Qiao

In this paper, a method is proposed for finding a pixel transformation function that maximizes backlight dimming while maintaining a pre-specified image distortion level for a liquid crystal display. This is achieved by finding a pixel…

其他计算机科学 · 计算机科学 2011-11-09 Ali Iranli , Hanif Fatemi , Massoud Pedram

We present a neural-based model for relighting a half-body portrait image by simply referring to another portrait image with the desired lighting condition. Rather than following classical inverse rendering methodology that involves…

图形学 · 计算机科学 2021-06-28 Guoxian Song , Tat-Jen Cham , Jianfei Cai , Jianmin Zheng

In this paper we are extracting surface reflectance and natural environmental illumination from a reflectance map, i.e. from a single 2D image of a sphere of one material under one illumination. This is a notoriously difficult problem, yet…

计算机视觉与模式识别 · 计算机科学 2016-03-29 Stamatios Georgoulis , Konstantinos Rematas , Tobias Ritschel , Mario Fritz , Luc Van Gool , Tinne Tuytelaars

Hyperspectral (HS) unmixing is the process of decomposing an HS image into material-specific spectra (endmembers) and their spatial distributions (abundance maps). Existing unmixing methods have two limitations with respect to noise…

图像与视频处理 · 电气工程与系统科学 2024-03-20 Kazuki Naganuma , Shunsuke Ono

Low-light images suffer from severe noise and low illumination. Current deep learning models that are trained with real-world images have excellent noise reduction, but a ratio parameter must be chosen manually to complete the enhancement…

图像与视频处理 · 电气工程与系统科学 2020-04-23 Qingxu Fu , Xiaoguang Di , Yu Zhang

Infrared image helps improve the perception capabilities of autonomous driving in complex weather conditions such as fog, rain, and low light. However, infrared image often suffers from low contrast, especially in non-heat-emitting targets…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Siyuan Chai , Xiaodong Guo , Tong Liu

Image denoising is a typical ill-posed problem due to complex degradation. Leading methods based on normalizing flows have tried to solve this problem with an invertible transformation instead of a deterministic mapping. However, the…

计算机视觉与模式识别 · 计算机科学 2023-02-01 Wenchao Du , Hu Chen , Yi Zhang , H. Yang

Low-light image enhancement (LLIE) techniques attempt to increase the visibility of images captured in low-light scenarios. However, as a result of enhancement, a variety of image degradations such as noise and color bias are revealed.…

图像与视频处理 · 电气工程与系统科学 2024-09-10 Savvas Panagiotou , Anna S. Bosman

All existing image enhancement methods, such as HDR tone mapping, cannot recover A/D quantization losses due to insufficient or excessive lighting, (underflow and overflow problems). The loss of image details due to A/D quantization is…

计算机视觉与模式识别 · 计算机科学 2018-03-22 Chang Liu , Xiaolin Wu , Xiao Shu

While deep learning methods have achieved notable progress in shadow removal, many existing approaches rely on shadow masks that are difficult to obtain, limiting their generalization to real-world scenes. In this work, we propose ReHiT, an…

计算机视觉与模式识别 · 计算机科学 2025-04-22 Wei Dong , Han Zhou , Seyed Amirreza Mousavi , Jun Chen

Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in…

图像与视频处理 · 电气工程与系统科学 2021-12-14 Hochang Rhee , Yeong Il Jang , Seyun Kim , Nam Ik Cho

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing…

计算机视觉与模式识别 · 计算机科学 2022-12-23 Tao Wang , Kaihao Zhang , Tianrun Shen , Wenhan Luo , Bjorn Stenger , Tong Lu

Low-light images are not conducive to human observation and computer vision algorithms due to their low visibility. Although many image enhancement techniques have been proposed to solve this problem, existing methods inevitably introduce…

计算机视觉与模式识别 · 计算机科学 2017-11-03 Zhenqiang Ying , Ge Li , Wen Gao

As critical visual details become obscured, the low visibility and high ISO noise in extremely low-light images pose a significant challenge to human pose estimation. Current methods fail to provide high-quality representations due to…

计算机视觉与模式识别 · 计算机科学 2025-01-15 Feng Zhang , Ze Li , Xiatian Zhu , Lei Chen

Image-based rendering techniques stand at the core of an immersive experience for the user, as they generate novel views given a set of multiple input images. Since they have shown good performance in terms of objective and subjective…

多媒体 · 计算机科学 2023-09-13 Marta Milovanović , Enzo Tartaglione , Marco Cagnazzo , Félix Henry