English
Related papers

Related papers: Relighting Images in the Wild with a Self-Supervis…

200 papers

We introduce SynthLight, a diffusion model for portrait relighting. Our approach frames image relighting as a re-rendering problem, where pixels are transformed in response to changes in environmental lighting conditions. Using a…

Computer Vision and Pattern Recognition · Computer Science 2025-01-17 Sumit Chaturvedi , Mengwei Ren , Yannick Hold-Geoffroy , Jingyuan Liu , Julie Dorsey , Zhixin Shu

In recent years, self-supervised learning has had significant success in applications involving computer vision and natural language processing. The type of pretext task is important to this boost in performance. One common pretext task is…

Computer Vision and Pattern Recognition · Computer Science 2022-01-24 Ademola Okerinde , Sam Hoggatt , Divya Vani Lakkireddy , Nolan Brubaker , William Hsu , Lior Shamir , Brian Spiesman

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…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Xu Wu , XianXu Hou , Zhihui Lai , Jie Zhou , Ya-nan Zhang , Witold Pedrycz , Linlin Shen

Reconstructing observed images from fMRI brain recordings is challenging. Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i.e., images with their corresponding fMRI responses) to span the huge space of natural images…

Image and Video Processing · Electrical Eng. & Systems 2021-06-11 Roman Beliy , Guy Gaziv , Assaf Hoogi , Francesca Strappini , Tal Golan , Michal Irani

Low-light images suffer from complex degradation, and existing enhancement methods often encode all degradation factors within a single latent space. This leads to highly entangled features and strong black-box characteristics, making the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Shuangli Du , Siming Yan , Zhenghao Shi , Zhenzhen You , Lu Sun

Illumination effects in images, specifically cast shadows and shading, have been shown to decrease the performance of deep neural networks on a large number of vision-based detection, recognition and segmentation tasks in urban driving…

Computer Vision and Pattern Recognition · Computer Science 2019-09-27 Alexandra Carlson , Ram Vasudevan , Matthew Johnson-Roberson

Depth estimation is a critical topic for robotics and vision-related tasks. In monocular depth estimation, in comparison with supervised learning that requires expensive ground truth labeling, self-supervised methods possess great potential…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Jinchang Zhang , Praveen Kumar Reddy , Xue-Iuan Wong , Yiannis Aloimonos , Guoyu Lu

Image contrast enhancement for outdoor vision is important for smart car auxiliary transport systems. The video frames captured in poor weather conditions are often characterized by poor visibility. Most image dehazing algorithms consider…

Computer Vision and Pattern Recognition · Computer Science 2015-10-06 Huimin Lu , Yujie Li , Shota Nakashima , Seiichi Serikawa

Most deep learning based image inpainting approaches adopt autoencoder or its variants to fill missing regions in images. Encoders are usually utilized to learn powerful representational spaces, which are important for dealing with…

Computer Vision and Pattern Recognition · Computer Science 2020-10-30 Xin Ma , Xiaoqiang Zhou , Huaibo Huang , Zhenhua Chai , Xiaolin Wei , Ran He

Blind deconvolution is a challenging problem, but in low-light it is even more difficult. Existing algorithms, both classical and deep-learning based, are not designed for this condition. When the photon shot noise is strong, conventional…

Image and Video Processing · Electrical Eng. & Systems 2022-11-21 Yash Sanghvi , Abhiram Gnanasambandam , Zhiyuan Mao , Stanley H. Chan

As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring model transparency. Existing methods achieve this attribution…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Zongfang Liu , Guangyi Chen , Boyang Sun , Tongliang Liu , Kun Zhang

Depth estimation from a single underwater image is one of the most challenging problems and is highly ill-posed. Due to the absence of large generalized underwater depth datasets and the difficulty in obtaining ground truth depth-maps,…

Computer Vision and Pattern Recognition · Computer Science 2019-05-29 Honey Gupta , Kaushik Mitra

Self-supervised learning (SSL) methods have achieved remarkable success in learning image representations allowing invariances in them - but therefore discarding transformation information that some computer vision tasks actually require.…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Qin Wang , Alessio Quercia , Benjamin Bruns , Abigail Morrison , Hanno Scharr , Kai Krajsek

We propose a neural inverse rendering approach that jointly reconstructs geometry, spatially varying reflectance, and lighting conditions from multi-view images captured under varying directional lighting. Unlike prior multi-view…

Computer Vision and Pattern Recognition · Computer Science 2025-08-01 Xu Cao , Takafumi Taketomi

Deep neural network based methods are the state of the art in various image restoration problems. Standard supervised learning frameworks require a set of noisy measurement and clean image pairs for which a distance between the output of…

Image and Video Processing · Electrical Eng. & Systems 2021-03-31 Rihuan Ke , Carola-Bibiane Schönlieb

Self-supervised learning has become a popular way to pretrain a deep learning model and then transfer it to perform downstream tasks. However, most of these methods are developed on large-scale image datasets that contain natural objects…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Kevin Van Vorst , Li Shen

Image alignment tasks require accurate pixel correspondences, which are usually recovered by matching local feature descriptors. Such descriptors are often derived using supervised learning on existing datasets with ground truth…

Computer Vision and Pattern Recognition · Computer Science 2018-08-07 Jing Dong , Byron Boots , Frank Dellaert , Ranveer Chandra , Sudipta N. Sinha

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

Camera arrays provide spatial and angular information within a single snapshot. With refocusing methods, focal planes can be altered after exposure. In this letter, we propose a light field refocusing method to improve the imaging quality…

Image and Video Processing · Electrical Eng. & Systems 2021-08-29 Yingqian Wang , Jungang Yang , Yulan Guo , Chao Xiao , Wei An

Single-view depth estimation refers to the ability to derive three-dimensional information per pixel from a single two-dimensional image. Single-view depth estimation is an ill-posed problem because there are multiple depth solutions that…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Javier Rodriguez-Puigvert