Papers › MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

MVSTER: Epipolar Transformer for Efficient Multi-View Stereo

15 Apr 2022arXiv:2204.07346archive 2025-07-28

XiaoFeng Wang, Zheng Zhu, Fangbo Qin, Yun Ye, Guan Huang, Xu Chi, Yijia He, Xingang Wang

Learning-based Multi-View Stereo (MVS) methods warp source images into the reference camera frustum to form 3D volumes, which are fused as a cost volume to be regularized by subsequent networks. The fusing step plays a vital role in bridging 2D semantics and 3D spatial associations. However, previous methods utilize extra networks to learn 2D information as fusing cues, underusing 3D spatial correlations and bringing additional computation costs. Therefore, we present MVSTER, which leverages the proposed epipolar Transformer to learn both 2D semantics and 3D spatial associations efficiently. Specifically, the epipolar Transformer utilizes a detachable monocular depth estimator to enhance 2D semantics and uses cross-attention to construct data-dependent 3D associations along epipolar line. Additionally, MVSTER is built in a cascade structure, where entropy-regularized optimal transport is leveraged to propagate finer depth estimations in each stage. Extensive experiments show MVSTER achieves state-of-the-art reconstruction performance with significantly higher efficiency: Compared with MVSNet and CasMVSNet, our MVSTER achieves 34% and 14% relative improvements on the DTU benchmark, with 80% and 51% relative reductions in running time. MVSTER also ranks first on Tanks&Temples-Advanced among all published works. Code is released at https://github.com/JeffWang987.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2204.07346")

Code

Syntology Ran 10 of 17 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 4 ran · our draft was wrong; 1 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jeffwang987/mvster officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 10 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · our draft was wrong
1ran · fixture could not drive it
5ran
7unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from JeffWang987/MVSTER. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Conv2d JeffWang987/MVSTER/models/MVS4Net.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3aafeb0680c73abf · report
ConvBnReLU3D JeffWang987/MVSTER/models/MVS4Net.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 2a8c0668448c2f85 · report
FPN4 JeffWang987/MVSTER/models/MVS4Net.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 38d084809ff8b324 · report
homo_warping JeffWang987/MVSTER/models/MVS4Net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 0335666ff3549d14 · report
init_inverse_range JeffWang987/MVSTER/models/MVS4Net.py official repository ran · our draft was wrong MIT (permissive) · 9dc0b1027a30eb55 · report
init_range JeffWang987/MVSTER/models/MVS4Net.py official repository ran · our draft was wrong MIT (permissive) · c72a4a2293997c31 · report
reg2d JeffWang987/MVSTER/models/MVS4Net.py official repository ran · metamorphic tier: deterministic MIT (permissive) · d6051468a8c98437 · report
reg3d JeffWang987/MVSTER/models/MVS4Net.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 23a0bbc6e0990065 · report
schedule_inverse_range JeffWang987/MVSTER/models/MVS4Net.py official repository ran · our draft was wrong MIT (permissive) · afbfac7ff243b94d · report
schedule_range JeffWang987/MVSTER/models/MVS4Net.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 1221de2433902805 · report
ASFF JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · 71a82dc67c29d4b3 · report
MVS4net JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · 594ae94979f60345 · report
NA_DCN JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · 20530c2983c968db · report
init_bn JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · e59939cd1cb63bd9 · report
init_uniform JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · a3982dbf26fc8521 · report
mono_depth_decoder JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · e8f23f1f97acdbff · report
stagenet JeffWang987/MVSTER/models/MVS4Net.py official repository unverified MIT (permissive) · 66e954624f370968 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections