English
Related papers

Related papers: XRefine: Attention-Guided Keypoint Match Refinemen…

200 papers

We propose SparseContrast, a new framework that merges dynamic sparse attention with contrastive learning for medical imaging, with a focus on chest X-ray disease detection in low-data settings. Traditional contrastive learning methods rely…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Paarth Prasad , Ruchika Malhotra

We present the backbone method, a generic framework that enables sparse and interpretable supervised machine learning methods to scale to ultra-high dimensional problems. We solve sparse regression problems with $10^7$ features in minutes…

Machine Learning · Computer Science 2022-07-19 Dimitris Bertsimas , Vassilis Digalakis

Matrix completion constantly receives tremendous attention from many research fields. It is commonly applied for recommender systems such as movie ratings, computer vision such as image reconstruction or completion, multi-task learning such…

Machine Learning · Computer Science 2019-10-08 Abdallah Chehade , Zunya Shi

Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applications such as autonomous driving, 3D reconstruction, augmented…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Junjie Hu , Chenyu Bao , Mete Ozay , Chenyou Fan , Qing Gao , Honghai Liu , Tin Lun Lam

In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric…

Robotics · Computer Science 2025-12-30 Raman Jha , Yang Zhou , Giuseppe Loianno

Small inter-class and large intra-class variations are the main challenges in fine-grained visual classification. Objects from different classes share visually similar structures and objects in the same class can have different poses and…

Computer Vision and Pattern Recognition · Computer Science 2019-09-09 Amir Erfan Eshratifar , David Eigen , Michael Gormish , Massoud Pedram

Localized features such as singularities, sharp gradients, discontinuities, and moving sources require adaptive finite element discretizations. Conventional refinement strategies introduce significant computational overhead through…

Computational Engineering, Finance, and Science · Computer Science 2026-04-29 Jan Niklas Schmäke , Martin Ruess

Camera relocalization involving a prior 3D reconstruction plays a crucial role in many mixed reality and robotics applications. Estimating the camera pose directly with respect to pre-built 3D models can be prohibitively expensive for…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Thuan B. Bui , Dinh-Tuan Tran , Joo-Ho Lee

This paper presents a new algorithmic framework for computing sparse solutions to large-scale linear discrete ill-posed problems. The approach is motivated by recent perspectives on iteratively reweighted norm schemes, viewed through the…

Numerical Analysis · Mathematics 2025-02-05 Lucas Onisk , Malena Sabaté Landman

Category-agnostic pose estimation aims to locate keypoints on query images according to a few annotated support images for arbitrary novel classes. Existing methods generally extract support features via heatmap pooling, and obtain…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Junjie Chen , Weilong Chen , Yifan Zuo , Yuming Fang

3D single object tracking is a key task in 3D computer vision. However, the sparsity of point clouds makes it difficult to compute the similarity and locate the object, posing big challenges to the 3D tracker. Previous works tried to solve…

Computer Vision and Pattern Recognition · Computer Science 2022-10-04 Yubo Cui , Jiayao Shan , Zuoxu Gu , Zhiheng Li , Zheng Fang

Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visual localization, 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Shihua Zhang , Zizhuo Li , Kaining Zhang , Yifan Lu , Yuxin Deng , Linfeng Tang , Xingyu Jiang , Jiayi Ma

Recent Reference-Based image super-resolution (RefSR) has improved SOTA deep methods introducing attention mechanisms to enhance low-resolution images by transferring high-resolution textures from a reference high-resolution image. The main…

Computer Vision and Pattern Recognition · Computer Science 2023-10-03 Esteban Reyes-Saldana , Mariano Rivera

We present an approach to matching images of objects in fine-grained datasets without using part annotations, with an application to the challenging problem of weakly supervised single-view reconstruction. This is in contrast to prior works…

Computer Vision and Pattern Recognition · Computer Science 2016-06-21 Angjoo Kanazawa , David W. Jacobs , Manmohan Chandraker

We present Rewis3d, a framework that leverages recent advances in feed-forward 3D reconstruction to significantly improve weakly supervised semantic segmentation on 2D images. Obtaining dense, pixel-level annotations remains a costly…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Jonas Ernst , Wolfgang Boettcher , Lukas Hoyer , Jan Eric Lenssen , Bernt Schiele

Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds. Meanwhile, diffusion models have shown appealing performance in generating…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Li Xu , Haoxuan Qu , Yujun Cai , Jun Liu

The performance of image based stereo estimation suffers from lighting variations, repetitive patterns and homogeneous appearance. Moreover, to achieve good performance, stereo supervision requires sufficient densely-labeled data, which are…

Computer Vision and Pattern Recognition · Computer Science 2020-05-06 Yu-Kai Huang , Yueh-Cheng Liu , Tsung-Han Wu , Hung-Ting Su , Winston H. Hsu

We propose a way to train deep learning based keypoint descriptors that makes them approximately equivariant for locally affine transformations of the image plane. The main idea is to use the representation theory of GL(2) to generalize the…

Computer Vision and Pattern Recognition · Computer Science 2024-08-27 Georg Bökman , Johan Edstedt , Michael Felsberg , Fredrik Kahl

We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences. GeoRefine consists of three modules: a hybrid SLAM module using learning-based priors, an online…

Computer Vision and Pattern Recognition · Computer Science 2022-05-04 Pan Ji , Qingan Yan , Yuxin Ma , Yi Xu

Generating 3D models from multi-view 2D RGB images has gained significant attention, extending the capabilities of technologies like Virtual Reality, Robotic Vision, and human-machine interaction. In this paper, we introduce a hybrid…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Ajith Balakrishnan , Sreeja S , Linu Shine