English
Related papers

Related papers: Multi-View Stereo by Temporal Nonparametric Fusion

200 papers

In this paper we present a novel approach for bottom-up multi-person 3D human pose estimation from monocular RGB images. We propose to use high resolution volumetric heatmaps to model joint locations, devising a simple and effective…

Computer Vision and Pattern Recognition · Computer Science 2020-04-02 Matteo Fabbri , Fabio Lanzi , Simone Calderara , Stefano Alletto , Rita Cucchiara

Vision-Language Models (VLMs) learn joint representations by mapping images and text into a shared latent space. However, recent research highlights that deterministic embeddings from standard VLMs often struggle to capture the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Aishwarya Venkataramanan , Paul Bodesheim , Joachim Denzler

We develop a robust data fusion algorithm for field reconstruction of multiple physical phenomena. The contribution of this paper is twofold: First, we demonstrate how multi-spatial fields which can have any marginal distributions and…

Methodology · Statistics 2019-06-11 Pengfei Zhang , Gareth W. Peters , Ido Nevat , Keng Boon Teo , Yixin Wang

Depth estimation, as a necessary clue to convert 2D images into the 3D space, has been applied in many machine vision areas. However, to achieve an entire surrounding 360-degree geometric sensing, traditional stereo matching algorithms for…

Computer Vision and Pattern Recognition · Computer Science 2021-09-22 Keyang Zhou , Kailun Yang , Kaiwei Wang

Inter-person occlusion and depth ambiguity make estimating the 3D poses of monocular multiple persons as camera-centric coordinates a challenging problem. Typical top-down frameworks suffer from high computational redundancy with an…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Juze Zhang , Jingya Wang , Ye Shi , Fei Gao , Lan Xu , Jingyi Yu

We present LCollision, a learning-based method that synthesizes collision-free 3D human poses. At the crux of our approach is a novel deep architecture that simultaneously decodes new human poses from the latent space and predicts colliding…

Graphics · Computer Science 2021-03-19 Qingyang Tan , Zherong Pan , Dinesh Manocha

We present a novel multi-altitude camera pose estimation system, addressing the challenges of robust and accurate localization across varied altitudes when only considering sparse image input. The system effectively handles diverse…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Yaxuan Li , Yewei Huang , Bijay Gaudel , Hamidreza Jafarnejadsani , Brendan Englot

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs)…

Computer Vision and Pattern Recognition · Computer Science 2015-08-03 Mehrtash Harandi , Mathieu Salzmann , Mahsa Baktashmotlagh

Representing scenes with multiple semi-transparent colored layers has been a popular and successful choice for real-time novel view synthesis. Existing approaches infer colors and transparency values over regularly-spaced layers of planar…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Taras Khakhulin , Denis Korzhenkov , Pavel Solovev , Gleb Sterkin , Timotei Ardelean , Victor Lempitsky

Multi-view Stereo (MVS) aims to estimate depth and reconstruct 3D point clouds from a series of overlapping images. Recent learning-based MVS frameworks overlook the geometric information embedded in features and correlations, leading to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Yuxi Hu , Jun Zhang , Zhe Zhang , Rafael Weilharter , Yuchen Rao , Kuangyi Chen , Runze Yuan , Friedrich Fraundorfer

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Edoardo Remelli , Shangchen Han , Sina Honari , Pascal Fua , Robert Wang

Recent feed-forward 3D gaussian splatting methods have made dramatic progress on individual aspects of 3D scene reconstruction, but no existing method jointly addresses dynamic content, multi-view input, and unknown camera poses in a single…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Matteo Balice , Yanik Kunzi , Chenyangguang Zhang , Matteo Matteucci , Marc Pollefeys , Sungwhan Hong

This paper presents a computational framework for accurately estimating the disparity map of plenoptic images. The proposed framework is based on the variational principle and provides intrinsic sub-pixel precision. The light-field motion…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Trung-Hieu Tran , Zhe Wang , Sven Simon

Sparse-view scene reconstruction often faces significant challenges due to the constraints imposed by limited observational data. These limitations result in incomplete information, leading to suboptimal reconstructions using existing…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Xiangyu Sun , Runnan Chen , Mingming Gong , Dong Xu , Tongliang Liu

We present a novel deep learning architecture for fusing static multi-exposure images. Current multi-exposure fusion (MEF) approaches use hand-crafted features to fuse input sequence. However, the weak hand-crafted representations are not…

Computer Vision and Pattern Recognition · Computer Science 2017-12-21 K. Ram Prabhakar , V. Sai Srikar , R. Venkatesh Babu

Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fields, which might incur numerous irrelevant cues, such as a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Runyang Feng , Yixing Gao , Xueqing Ma , Tze Ho Elden Tse , Hyung Jin Chang

Explicitly modeling room background depth as a geometric constraint has proven effective for panoramic depth estimation. However, reconstructing this background depth for regular enclosed regions in a complex indoor scene without external…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Kanglin Ning , Ruzhao Chen , Penghong Wang , Xingtao Wang , Ruiqin Xiong , Xiaopeng Fan

Recently, generalizable human Gaussian splatting from sparse-view inputs has been actively studied for the photorealistic human rendering. Most existing methods rely on explicit geometric constraints or predefined structural representations…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Jingi Kim , Wonjun Kim

The method of deep learning has achieved excellent results in improving the performance of robotic grasping detection. However, the deep learning methods used in general object detection are not suitable for robotic grasping detection.…

Computer Vision and Pattern Recognition · Computer Science 2021-01-26 Hu Cao , Guang Chen , Zhijun Li , Jianjie Lin , Alois Knoll

Learning methods for relative camera pose estimation have been developed largely in isolation from classical geometric approaches. The question of how to integrate predictions from deep neural networks (DNNs) and solutions from geometric…

Computer Vision and Pattern Recognition · Computer Science 2021-04-19 Bingbing Zhuang , Manmohan Chandraker
‹ Prev 1 8 9 10 Next ›