English
Related papers

Related papers: Self-Supervised Shadow Removal

200 papers

This paper proposes a novel self-supervised learning method for semantic segmentation using selective masking image reconstruction as the pretraining task. Our proposed method replaces the random masking augmentation used in most masked…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Yuemin Wang , Ian Stavness

Shadows in videos are difficult to detect because of the large shadow deformation between frames. In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method. To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Lihao Liu , Jean Prost , Lei Zhu , Nicolas Papadakis , Pietro Liò , Carola-Bibiane Schönlieb , Angelica I Aviles-Rivero

Shadows cast by terrain and tall structures remain a major obstacle for high-resolution satellite image analysis, degrading classification, detection, and 3D reconstruction performance. Public resources offering geometry-consistent paired…

Computer Vision and Pattern Recognition · Computer Science 2026-05-06 Lorenzo Beltrame , Jules Salzinger , Filip Svoboda , Phillipp Fanta-Jende , Jasmin Lampert , Radu Timofte , Marco Körner

Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Evgenii Zheltonozhskii , Chaim Baskin , Alex M. Bronstein , Avi Mendelson

Image deblurring aims to restore the latent sharp images from the corresponding blurred ones. In this paper, we present an unsupervised method for domain-specific single-image deblurring based on disentangled representations. The…

Computer Vision and Pattern Recognition · Computer Science 2019-08-06 Boyu Lu , Jun-Cheng Chen , Rama Chellappa

State-of-the-art methods for 3D reconstruction of faces from a single image require 2D-3D pairs of ground-truth data for supervision. Such data is costly to acquire, and most datasets available in the literature are restricted to pairs for…

Computer Vision and Pattern Recognition · Computer Science 2018-12-19 Yifan Xing , Rahul Tewari , Paulo R. S. Mendonca

We propose a relighting method for outdoor images. Our method mainly focuses on predicting cast shadows in arbitrary novel lighting directions from a single image while also accounting for shading and global effects such the sun light color…

Graphics · Computer Science 2022-04-21 David Griffiths , Tobias Ritschel , Julien Philip

Shadow removal is an essential task for scene understanding. Many studies consider only matching the image contents, which often causes two types of ghosts: color in-consistencies in shadow regions or artifacts on shadow boundaries. In this…

Computer Vision and Pattern Recognition · Computer Science 2019-11-22 Xiaodong Cun , Chi-Man Pun , Cheng Shi

With the advent of advances in self-supervised learning, paired clean-noisy data are no longer required in deep learning-based image denoising. However, existing blind denoising methods still require the assumption with regard to noise…

Computer Vision and Pattern Recognition · Computer Science 2021-09-10 Kanggeun Lee , Won-Ki Jeong

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Rabia Ali , Muhammad Umar Karim Khan , Chong Min Kyung

The lack of large-scale noisy-clean image pairs restricts supervised denoising methods' deployment in actual applications. While existing unsupervised methods are able to learn image denoising without ground-truth clean images, they either…

Computer Vision and Pattern Recognition · Computer Science 2022-03-23 Yi Zhang , Dasong Li , Ka Lung Law , Xiaogang Wang , Hongwei Qin , Hongsheng Li

When capturing images in low-light conditions, the images often suffer from low visibility, which not only degrades the visual aesthetics of images, but also significantly degenerates the performance of many computer vision algorithms. In…

Computer Vision and Pattern Recognition · Computer Science 2020-12-17 Lijun Zhang , Xiao Liu , Erik Learned-Miller , Hui Guan

This project aims to adopt preprocessing operations to get less distortions for shadow image enlargement. The preprocessing operations consists of three main steps: first enlarge the original shadow image by using any kind of interpolation…

Computer Vision and Pattern Recognition · Computer Science 2021-02-24 Raid R. Al-Nima , Ali N. Hamoodi , Radhwan Y. Al-Jawadi , Ziad S. Mohammad

Text-to-image diffusion models excel at generating diverse portraits, but lack intuitive shadow control. Existing editing approaches, as post-processing, struggle to offer effective manipulation across diverse styles. Additionally, these…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Haoming Cai , Tsung-Wei Huang , Shiv Gehlot , Brandon Y. Feng , Sachin Shah , Guan-Ming Su , Christopher Metzler

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,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Puntawat Ponglertnapakorn , Nontawat Tritrong , Supasorn Suwajanakorn

Scene text erasing seeks to erase text contents from scene images and current state-of-the-art text erasing models are trained on large-scale synthetic data. Although data synthetic engines can provide vast amounts of annotated training…

Computer Vision and Pattern Recognition · Computer Science 2023-05-01 Xiangcheng Du , Zhao Zhou , Yingbin Zheng , Xingjiao Wu , Tianlong Ma , Cheng Jin

As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, remote sensing, biomedical imaging, etc. In any domain,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Hassan Baker , Matthew S. Emigh , Austin J. Brockmeier

We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision. Recent advances have shifted the interest towards directly regressing parameters of a…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Jogendra Nath Kundu , Mugalodi Rakesh , Varun Jampani , Rahul Mysore Venkatesh , R. Venkatesh Babu

Recent advances in 3D deep learning have shown that it is possible to train highly effective deep models for 3D shape generation, directly from 2D images. This is particularly interesting since the availability of 3D models is still limited…

Computer Vision and Pattern Recognition · Computer Science 2019-11-05 Shichen Liu , Shunsuke Saito , Weikai Chen , Hao Li

Deep learning has demonstrated its power in image rectification by leveraging the representation capacity of deep neural networks via supervised training based on a large-scale synthetic dataset. However, the model may overfit the synthetic…

Computer Vision and Pattern Recognition · Computer Science 2021-06-21 Jinlong Fan , Jing Zhang , Dacheng Tao