{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/transmvsnet-global-context-aware-multi-view","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","arxiv_id":"2111.14600","date":"2021-11-29","proceeding":"CVPR 2022 1","authors":["Yikang Ding","Wentao Yuan","Qingtian Zhu","Haotian Zhang","Xiangyue Liu","Yuanjiang Wang","Xiao Liu"],"abstract":"In this paper, we present TransMVSNet, based on our exploration of feature matching in multi-view stereo (MVS). We analogize MVS back to its nature of a feature matching task and therefore propose a powerful Feature Matching Transformer (FMT) to leverage intra- (self-) and inter- (cross-) attention to aggregate long-range context information within and across images. To facilitate a better adaptation of the FMT, we leverage an Adaptive Receptive Field (ARF) module to ensure a smooth transit in scopes of features and bridge different stages with a feature pathway to pass transformed features and gradients across different scales. In addition, we apply pair-wise feature correlation to measure similarity between features, and adopt ambiguity-reducing focal loss to strengthen the supervision. To the best of our knowledge, TransMVSNet is the first attempt to leverage Transformer into the task of MVS. As a result, our method achieves state-of-the-art performance on DTU dataset, Tanks and Temples benchmark, and BlendedMVS dataset. The code of our method will be made available at https://github.com/MegviiRobot/TransMVSNet .","url_abs":"https://arxiv.org/abs/2111.14600v1","url_pdf":"https://arxiv.org/pdf/2111.14600v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"transmvsnet-global-context-aware-multi-view","repo_url":"https://github.com/megviirobot/transmvsnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"feature-correlation","task_name":"Feature Correlation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"focal-loss","method_name":"Focal Loss"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-reconstruction-on-dtu","task":"3D Reconstruction","dataset":"DTU","model":"TransMVSNet","rank_in_archive_order":9,"of":24,"metrics":{"Acc":"0.321","Comp":"0.289","Overall":"0.305"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.14600","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}