首页/论文/2003.00711

arXiv 2003.007112020-03-02cs.CV

A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation

Shenzhen Evomotion Co., Ltd（深圳进化动力科技有限公司）

Sizhang Dai, Weibing Huang

英文摘要：

We propose a learning-based network for depth map estimation from multi-view stereo (MVS) images. Our proposed network consists of three sub-networks: 1) a base network for initial depth map estimation from an unstructured stereo image pair, 2) a novel refinement network that leverages both photometric and geometric information, and 3) an attentional multi-view aggregation framework that enables efficient information exchange and integration among different stereo image pairs. The proposed network, called A-TVSNet, is evaluated on various MVS datasets and shows the ability to produce high quality depth map that outperforms competing approaches. Our code is available at https://github.com/daiszh/A-TVSNet.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

分割感知先验辅助的联合全局信息聚合三维建筑物重建

Segmentation-aware Prior Assisted Joint Global Information Aggregated 3D Building Reconstruction

Guangdong University of Technology（广东工业大学）；Huazhong University of Science and Technology（华中科技大学）

针对多视图立体在大规模建筑弱纹理区域匹配失效的问题，提出基于 SAM 与 RANSAC 的平面先验构建和全局信息聚合代价函数，提升三维建筑重建的完整性与密度。

2024-10-24cs.CV

Planar Prior Assisted PatchMatch Multi-View Stereo

National Key Laboratory of Science and Technology on Multispectral Information Processing（多光谱信息处理科学技术国家重点实验室）

The completeness of 3D models is still a challenging problem in multi-view stereo (MVS) due to the unreliable photometric consistency in low-textured areas. Since low-textured areas usually exhibit strong planarity, planar models are advantageous to the depth estimation of low-textured areas. On the other hand, PatchMatch multi-view stereo is very efficient for its sampling and propagation scheme. By taking advantage of planar models and PatchMatch multi-view stereo, we propose a planar prior assisted PatchMatch multi-view stereo framework in this paper. In detail, we utilize a probabilistic g…

2019-12-26cs.CV

MVPSNet：快速可泛化的多视角光度立体

MVPSNet: Fast Generalizable Multi-view Photometric Stereo

University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）；University of Maryland, College Park（马里兰大学帕克分校）

提出MVPSNet，一种快速可泛化的多视角光度立体解决方案，通过光照聚合特征图（LAFM）从多光照图像中提取几何特征进行立体匹配，在无纹理区域表现优异，推理速度比PS-NeRF快411倍，并引入新合成数据集sMVPS。

2023-05-18cs.CV

ChiTransformer：迈向基于线索的可靠立体视觉

ChiTransformer:Towards Reliable Stereo from Cues

Georgia State University（佐治亚州立大学）

本文提出受视交叉启发的自监督双目深度估计网络 ChiTransformer，通过 ViT、GPCA 与混合层融合单目线索和跨视图模式，性能提升11%，并适用于鱼眼等非直线图像。

2023-11-01cs.CV

Curvature-guided dynamic scale networks for Multi-view Stereo

KAIST（韩国科学技术院）；ETRI（韩国电子通信研究院）

Multi-view stereo (MVS) is a crucial task for precise 3D reconstruction. Most recent studies tried to improve the performance of matching cost volume in MVS by designing aggregated 3D cost volumes and their regularization. This paper focuses on learning a robust feature extraction network to enhance the performance of matching costs without heavy computation in the other steps. In particular, we present a dynamic scale feature extraction network, namely, CDSFNet. It is composed of multiple novel convolution layers, each of which can select a proper patch scale for each pixel guided by the norm…

2022-03-10cs.AIcs.CVcs.GR

SweepNet: Wide-baseline Omnidirectional Depth Estimation

Hanyang University（汉阳大学）

Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions. In this paper, we propose a novel wide-baseline omnidirectional stereo algorithm which computes the dense depth estimate from the fisheye images using a deep convolutional neural network. The capture system consists of multiple cameras mounted on a wide-baseline rig with ultrawide field of view (FOV) lenses, and we present the calibration algorithm for the extrinsic parameters based on the bundle adjustment. I…

2019-08-16cs.CV

更多相关论文收起更多论文

MSDC-Net: Multi-Scale Dense and Contextual Networks for Automated Disparity Map for Stereo Matching

Northwestern Polytechnical University（西北工业大学）；Nanyang Technological University（南洋理工大学）

Disparity prediction from stereo images is essential to computer vision applications including autonomous driving, 3D model reconstruction, and object detection. To predict accurate disparity map, we propose a novel deep learning architecture for detectingthe disparity map from a rectified pair of stereo images, called MSDC-Net. Our MSDC-Net contains two modules: multi-scale fusion 2D convolution and multi-scale residual 3D convolution modules. The multi-scale fusion 2D convolution module exploits the potential multi-scale features, which extracts and fuses the different scale features by Dens…

2019-04-30cs.CV

Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation

East China Normal University（华东师范大学）

Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views facilitates the SR performance, while the high-resolution (HR) features with richer details benefit the correspondence estimation. According to this motivation, we propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which simultaneously handles the stereo image super-resolution and disparity estimation in a unified frame…

2021-06-02cs.CV

GoMVS：面向多视图立体匹配的几何一致性代价聚合

GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo

Northwestern Polytechnical University（西北工业大学）；ETH Zürich（苏黎世联邦理工学院）；University of Tübingen（蒂宾根大学）

针对多视图立体匹配中直接聚合相邻代价存在局部几何不一致的问题，提出GoMVS方法，通过GCP模块结合几何平滑性与表面法向量实现几何一致性代价聚合，在多个基准数据集上取得SOTA性能。

2024-04-11cs.CV

DVP-MVS: 协同深度边缘与可视性先验用于多视图立体

DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo

DVP-MVS通过协同深度边缘与可视性先验，改进多视图立体中的补丁变形，提升鲁棒性和泛化能力。

2025-11-25cs.CV

DVP-MVS++: 融合深度-法线-边缘与协调视图先验以实现多视图立体摄影

DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo

Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；DSLAB, School of Information Science & Engineering, Lanzhou University（兰州大学信息科学与工程学院DSLAB）；School of Mathematical Science, Jiangsu University（江苏大学数学学院）；MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China（中国科学技术大学脑科学与智能感知教育部重点实验室）；Agricultural Information Institute, Chinese Academy of Agricultural Sciences（中国农业科学院农业信息研究所）；Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs（农业农村部农业大数据重点实验室）

本文提出DVP-MVS++方法，通过融合深度-法线-边缘对齐和协调跨视图先验，提升多视图立体摄影中鲁棒性和视图感知的补丁变形能力。

2026-04-17cs.CV

Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Function

Nanjing University（南京大学）；iQIYI Inc（爱奇艺公司）

Recovering detailed facial geometry from a set of calibrated multi-view images is valuable for its wide range of applications. Traditional multi-view stereo (MVS) methods adopt an optimization-based scheme to regularize the matching cost. Recently, learning-based methods integrate all these into an end-to-end neural network and show superiority of efficiency. In this paper, we propose a novel architecture to recover extremely detailed 3D faces within dozens of seconds. Unlike previous learning-based methods that regularize the cost volume via 3D CNN, we propose to learn an implicit function fo…

2022-05-05cs.CV

DORT：在循环中建模动态物体用于多相机3D目标检测与跟踪

DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking

Shanghai AI Laboratory（上海人工智能实验室）；The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）

DORT针对多相机3D检测中忽略物体运动导致定位偏差的问题，提出在循环中建模动态物体，通过物体级局部体素迭代优化运动与位置，实现精确跨帧特征聚合，并在nuScenes检测与跟踪上取得领先性能。

2023-04-19cs.CV