中文
相关论文

相关论文: Stronger Semantic Encoders Can Harm Relighting Per…

200 篇论文

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations; (2) loss of texture and color information caused…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Xu Wu , XianXu Hou , Zhihui Lai , Jie Zhou , Ya-nan Zhang , Witold Pedrycz , Linlin Shen

Deep learning algorithms lack human-interpretable accounts of how they transform raw visual input into a robust semantic understanding, which impedes comparisons between different architectures, training objectives, and the human brain. In…

计算机视觉与模式识别 · 计算机科学 2024-04-30 Gustaw Opiełka , Jessica Loke , Steven Scholte

Image relighting is the task of showing what a scene from a source image would look like if illuminated differently. Inverse graphics schemes recover an explicit representation of geometry and a set of chosen intrinsics, then relight with…

计算机视觉与模式识别 · 计算机科学 2025-04-08 Xiao Zhang , William Gao , Seemandhar Jain , Michael Maire , David A. Forsyth , Anand Bhattad

Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and…

图像与视频处理 · 电气工程与系统科学 2024-10-28 Daxin Li , Yuanchao Bai , Kai Wang , Junjun Jiang , Xianming Liu

The task of extracting intrinsic components, such as reflectance and shading, from neural radiance fields is of growing interest. However, current methods largely focus on synthetic scenes and isolated objects, overlooking the complexities…

计算机视觉与模式识别 · 计算机科学 2024-06-18 Yixiong Yang , Shilin Hu , Haoyu Wu , Ramon Baldrich , Dimitris Samaras , Maria Vanrell

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

This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex…

计算机视觉与模式识别 · 计算机科学 2025-09-12 Xiaodong Wang , Zijun He , Xin Yuan

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

计算机视觉与模式识别 · 计算机科学 2025-12-22 Shilong Zhang , He Zhang , Zhifei Zhang , Chongjian Ge , Shuchen Xue , Shaoteng Liu , Mengwei Ren , Soo Ye Kim , Yuqian Zhou , Qing Liu , Daniil Pakhomov , Kai Zhang , Zhe Lin , Ping Luo

Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep…

计算机视觉与模式识别 · 计算机科学 2022-08-31 Partha Das , Sezer Karaoglu , Arjan Gijsenij , Theo Gevers

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

Image encoders, a fundamental component of vision-language models (VLMs), are typically pretrained independently before being aligned with a language model. This standard paradigm results in encoders that process images agnostically,…

计算机视觉与模式识别 · 计算机科学 2025-11-27 Raghuveer Thirukovalluru , Xiaochuang Han , Bhuwan Dhingra , Emily Dinan , Maha Elbayad

What happens when we push audio-visual alignment to its absolute limits? To systematically investigate this question, we needed datasets with granular alignment quality annotations, but existing datasets treat alignment as binary, either…

多媒体 · 计算机科学 2025-08-07 Ali Vosoughi , Jing Bi , Pinxin Liu , Yunlong Tang , Chenliang Xu

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily…

图像与视频处理 · 电气工程与系统科学 2023-01-12 Ezgi Ozyilkan , Mateen Ulhaq , Hyomin Choi , Fabien Racape

Current deep learning-based low-light image enhancement methods often struggle with high-resolution images, and fail to meet the practical demands of visual perception across diverse and unseen scenarios. In this paper, we introduce a novel…

计算机视觉与模式识别 · 计算机科学 2024-07-18 Tomáš Chobola , Yu Liu , Hanyi Zhang , Julia A. Schnabel , Tingying Peng

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional…

计算机视觉与模式识别 · 计算机科学 2020-05-28 Yunfei Liu , Yu Li , Shaodi You , Feng Lu

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregressive decoders often…

机器学习 · 计算机科学 2019-05-21 Bryan Seybold , Emily Fertig , Alex Alemi , Ian Fischer

There has long been a belief that high-level semantics learning can benefit various downstream computer vision tasks. However, in the low-light image enhancement (LLIE) community, existing methods learn a brutal mapping between low-light…

计算机视觉与模式识别 · 计算机科学 2025-04-29 Jialang Lu , Huayu Zhao , Huiyu Zhai , Xingxing Yang , Shini Han

Low-light image enhancement is an important task in computer vision, essential for improving the visibility and quality of images captured in non-optimal lighting conditions. Inadequate illumination can lead to significant information loss…

计算机视觉与模式识别 · 计算机科学 2025-05-15 Ezequiel Perez-Zarate , Oscar Ramos-Soto , Chunxiao Liu , Diego Oliva , Marco Perez-Cisneros

Reasoning-based image quality assessment (IQA) models trained through reinforcement learning (RL) exhibit exceptional generalization, yet the underlying mechanisms and critical factors driving this capability remain underexplored in current…

计算机视觉与模式识别 · 计算机科学 2026-03-04 Shijie Zhao , Xuanyu Zhang , Weiqi Li , Junlin Li , Li Zhang , Tianfan Xue , Jian Zhang

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Neha Kalibhat , Priyatham Kattakinda , Sumit Nawathe , Arman Zarei , Nikita Seleznev , Samuel Sharpe , Senthil Kumar , Soheil Feizi
‹ 上一页 1 2 3 10 下一页 ›