English
Related papers

Related papers: Understanding Multi-View Transformers

200 papers

Vision Transformers (ViTs) are normally regarded as a stack of transformer layers. In this work, we propose a novel view of ViTs showing that they can be seen as ensemble networks containing multiple parallel paths with different lengths.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Shuning Chang , Pichao Wang , Hao Luo , Fan Wang , Mike Zheng Shou

Recent advancements in learning-based Multi-View Stereo (MVS) methods have prominently featured transformer-based models with attention mechanisms. However, existing approaches have not thoroughly investigated the profound influence of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-23 Chenjie Cao , Xinlin Ren , Yanwei Fu

DUSt3R has recently shown that one can reduce many tasks in multi-view geometry, including estimating camera intrinsics and extrinsics, reconstructing the scene in 3D, and establishing image correspondences, to the prediction of a pair of…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Edgar Sucar , Zihang Lai , Eldar Insafutdinov , Andrea Vedaldi

Video stabilization aims to mitigate camera shake but faces a fundamental trade-off between geometric robustness and full-frame consistency. While 2D methods suffer from aggressive cropping, 3D techniques are often undermined by fragile…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Muhua Zhu , Xinhao Jin , Yu Zhang , Yifei Xue , Tie Ji , Yizhen Lao

Accurate and consistent 3D tracking from multiple cameras is a key component in a vision-based autonomous driving system. It involves modeling 3D dynamic objects in complex scenes across multiple cameras. This problem is inherently…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Tianyuan Zhang , Xuanyao Chen , Yue Wang , Yilun Wang , Hang Zhao

Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-19 Julian Ost , Tanushree Banerjee , Mario Bijelic , Felix Heide

To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches. However, due to the lack of accurate estimated depth,…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Ching-Yu Tseng , Yi-Rong Chen , Hsin-Ying Lee , Tsung-Han Wu , Wen-Chin Chen , Winston H. Hsu

We present STream3R, a novel approach to 3D reconstruction that reformulates pointmap prediction as a decoder-only Transformer problem. Existing state-of-the-art methods for multi-view reconstruction either depend on expensive global…

Computer Vision and Pattern Recognition · Computer Science 2025-08-15 Yushi Lan , Yihang Luo , Fangzhou Hong , Shangchen Zhou , Honghua Chen , Zhaoyang Lyu , Shuai Yang , Bo Dai , Chen Change Loy , Xingang Pan

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Kadir Yilmaz , Adrian Kruse , Tristan Höfer , Daan de Geus , Bastian Leibe

While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Benjamin Beilharz , Thomas S. A. Wallis

Multi-view projection techniques have shown themselves to be highly effective in achieving top-performing results in the recognition of 3D shapes. These methods involve learning how to combine information from multiple view-points. However,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Abdullah Hamdi , Faisal AlZahrani , Silvio Giancola , Bernard Ghanem

3D video coding is one of the most popular research area in multimedia. This paper reviews the recent progress of the coding technologies for multiview video (MVV) and free view-point video (FVV) which is represented by MVV and depth maps.…

Multimedia · Computer Science 2015-12-31 Qifei Wang

This paper proposes a network, referred to as MVSTR, for Multi-View Stereo (MVS). It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 Jie Zhu , Bo Peng , Wanqing Li , Haifeng Shen , Zhe Zhang , Jianjun Lei

We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a single forward pass. Drawing on the idea of ``looking broader to…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Gyeongjin Kang , Seungkwon Yang , Seungtae Nam , Younggeun Lee , Jungwoo Kim , Eunbyung Park

Inspired by the great success achieved by CNN in image recognition, view-based methods applied CNNs to model the projected views for 3D object understanding and achieved excellent performance. Nevertheless, multi-view CNN models cannot…

Computer Vision and Pattern Recognition · Computer Science 2021-10-26 Shuo Chen , Tan Yu , Ping Li

Transformer-based end-to-end speech recognition has achieved great success. However, the large footprint and computational overhead make it difficult to deploy these models in some real-world applications. Model compression techniques can…

Computation and Language · Computer Science 2023-03-15 Yifan Peng , Jaesong Lee , Shinji Watanabe

When interacting in a three dimensional world, humans must estimate 3D structure from visual inputs projected down to two dimensional retinal images. It has been shown that humans use the persistence of object shape over motion-induced…

Neurons and Cognition · Quantitative Biology 2023-04-03 Marissa Connor , Bruno Olshausen , Christopher Rozell

While weakly supervised multi-view face reconstruction (MVR) is garnering increased attention, one critical issue still remains open: how to effectively interact and fuse multiple image information to reconstruct high-precision 3D models.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-25 Weiguang Zhao , Chaolong Yang , Jianan Ye , Rui Zhang , Yuyao Yan , Xi Yang , Bin Dong , Amir Hussain , Kaizhu Huang

Single-image-to-3D generative models can now produce high-quality geometry, yet conditioning on a single view inevitably introduces ambiguity about unseen regions. Multi-view conditioning can reduce this ambiguity, but existing methods…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Hanxiao Sun , Mingxin Yang , Shuhui Yang , Zebin He , Xintong Han , Hongbo Fu , Chunchao Guo , Wenhan Luo

This paper presents an investigation of vision transformer learning for multi-view geometry tasks, such as optical flow estimation, by fine-tuning video foundation models. Unlike previous methods that involve custom architectural designs…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Huimin Wu , Kwang-Ting Cheng , Stephen Lin , Zhirong Wu