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 ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 10 ran (5 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jeffwang987/mvster officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 10 ran (5 instrument-failed) · 7 unverified 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 (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · our draft was wrong
1ran; the contract check could not run
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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

jeffwang987/mvster official repository 17 samples, 10 ran (5 instrument-failed) · 7 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
models/MVS4Net.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3aafeb0680c73abf · report fixture: returned Conv2d · level recorded 2026-09-22
ConvBnReLU3D models/MVS4Net.py ran · metamorphic tier: deterministic MIT (permissive) · 2a8c0668448c2f85 · report fixture: returned ConvBnReLU3D · level recorded 2026-09-22
FPN4 models/MVS4Net.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 38d084809ff8b324 · report fixture: returned FPN4 · level recorded 2026-09-22
homo_warping in 12 papers models/MVS4Net.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 0335666ff3549d14 · report fixture: signature src_fea:Tensor/4/float, src_proj:Tensor/3/float, ref_proj:Tensor/3/float, depth_values:Tensor/4/float, vis_ETA:bool/0/bool, fn:NoneType/0/? · returned Tensor · level recorded 2026-09-22
init_inverse_range models/MVS4Net.py ran · our draft was wrong MIT (permissive) · 9dc0b1027a30eb55 · report fixture: signature cur_depth:Tensor/2/float, ndepths:int/0/int, device:device/0/?, dtype:dtype/0/?, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
init_range models/MVS4Net.py ran · our draft was wrong MIT (permissive) · c72a4a2293997c31 · report fixture: signature cur_depth:Tensor/2/float, ndepths:int/0/int, device:str/0/str, dtype:dtype/0/?, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
reg2d models/MVS4Net.py ran · metamorphic tier: deterministic MIT (permissive) · d6051468a8c98437 · report fixture: returned reg2d · level recorded 2026-09-22
reg3d models/MVS4Net.py ran · metamorphic tier: deterministic MIT (permissive) · 23a0bbc6e0990065 · report fixture: returned reg3d · level recorded 2026-09-22
schedule_inverse_range models/MVS4Net.py ran · our draft was wrong MIT (permissive) · afbfac7ff243b94d · report fixture: signature inverse_min_depth:Tensor/3/float, inverse_max_depth:Tensor/3/float, ndepths:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
schedule_range models/MVS4Net.py ran · our draft was wrong fingerprinted MIT (permissive) · 1221de2433902805 · report fixture: signature cur_depth:Tensor/3/float, ndepth:int/0/int, depth_inteval_pixel:Tensor/1/float, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-22
ASFF models/MVS4Net.py unverified MIT (permissive) · 71a82dc67c29d4b3 · report
MVS4net models/MVS4Net.py unverified MIT (permissive) · 594ae94979f60345 · report
NA_DCN models/MVS4Net.py unverified MIT (permissive) · 20530c2983c968db · report
init_bn models/MVS4Net.py unverified MIT (permissive) · e59939cd1cb63bd9 · report
init_uniform models/MVS4Net.py unverified MIT (permissive) · a3982dbf26fc8521 · report
mono_depth_decoder models/MVS4Net.py unverified MIT (permissive) · e8f23f1f97acdbff · report
stagenet models/MVS4Net.py unverified MIT (permissive) · 66e954624f370968 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MVSTER (graph method: MVSTER). 17 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. MVS4net entry · level 0 · unverified · 594ae94979f60345
  2. ASFF helper · level 0 · unverified · 71a82dc67c29d4b3
  3. FPN4 helper · level 1 · ran · 38d084809ff8b324
  4. init_inverse_range helper · level 1 · ran · our draft was wrong · 9dc0b1027a30eb55
  5. init_range helper · level 1 · ran · our draft was wrong · c72a4a2293997c31
  6. mono_depth_decoder helper · level 0 · unverified · e8f23f1f97acdbff
  7. reg2d helper · level 1 · ran · d6051468a8c98437
  8. reg3d helper · level 1 · ran · 23a0bbc6e0990065
  9. schedule_inverse_range helper · level 1 · ran · our draft was wrong · afbfac7ff243b94d
  10. schedule_range helper · level 1 · ran · our draft was wrong · 1221de2433902805
  11. stagenet helper · level 0 · unverified · 66e954624f370968
  12. Conv2d helper · level 1 · ran · 3aafeb0680c73abf
  13. NA_DCN helper · level 0 · unverified · 20530c2983c968db
  14. ConvBnReLU3D helper · level 1 · ran · 2a8c0668448c2f85
  15. homo_warping model · level 1 · ran; the contract check could not run (RAISES) · 0335666ff3549d14
  16. init_bn helper · level 0 · unverified · e59939cd1cb63bd9
  17. init_uniform helper · level 0 · unverified · a3982dbf26fc8521

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2204.07346") returns these assemblies with each brick's role and wiring (how to connect).

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