Papers › When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo

When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo

29 Sep 2023ICCV 2023 1arXiv:2309.17218archive 2025-07-28

Tianqi Liu, Xinyi Ye, Weiyue Zhao, Zhiyu Pan, Min Shi, Zhiguo Cao

Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain non-local feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-to-line search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is available at https://github.com/TQTQliu/ET-MVSNet.

PaperPDFConference PDFCodeCode 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 13 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 8 ran (3 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 between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tqtqliu/et-mvsnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 8 ran (5 instrument-failed) · 5 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

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
3ran
5unverified

Licence: 0 of the 13 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 tqtqliu/et-mvsnet. “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”. “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.

tqtqliu/et-mvsnet official repository 13 samples, 8 ran (5 instrument-failed) · 5 unverified
MVS4net_loss models/MVS4Net.py ran MIT (permissive) · 9c73a828f8730bcc · report fixture: signature inputs:dict/0/?, depth_gt_ms:dict/0/?, mask_ms:dict/0/?, stage_lw:list/1/float, inverse_depth:bool/0/bool · returned tuple · level recorded 2026-09-24
cross_entropy_loss in 58 papers models/MVS4Net.py ran MIT (permissive) · 41f59aee24980c21 · report fixture: signature mask_true:Tensor/3/float, hypo_depth:Tensor/4/float, depth_gt:Tensor/3/float, attn_weight:Tensor/4/float · returned Tensor · level recorded 2026-09-25
homo_warping in 12 papers models/module.py ran MIT (permissive) · 2433e10d0340ac47 · report fixture: signature src_fea:Tensor/4/float, src_proj:Tensor/3/float, ref_proj:Tensor/3/float, depth_values:Tensor/4/float · returned Tensor · level recorded 2026-09-25
init_inverse_range models/module.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/module.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
make_nograd_func in 17 papers utils.py ran · our draft was wrong MIT (permissive) · a76fc7fb6958f97c · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
make_recursive_func in 15 papers utils.py ran · our draft was wrong MIT (permissive) · b62bec09ceeaca79 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
read_pfm in 24 papers datasets/data_io.py ran · our draft was wrong MIT (permissive) · 6b687b02c05fe850 · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-25
Blend_loss models/MVS4Net.py unverified MIT (permissive) · 46e1be8739ffd15e · report
MVS4net models/MVS4Net.py unverified MIT (permissive) · 683e0541c1d070c8 · report
tensor2float in 15 papers utils.py unverified MIT (permissive) · 8e28f96374f1b285 · report
train_sample train_bld.py unverified MIT (permissive) · acee5a023ac9e377 · report
train_sample train_dtu.py unverified MIT (permissive) · b6e60e102b3e750e · 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 ET-MVSNet (graph method: ET-MVSNet). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. MVS4net entry · level 0 · unverified · 683e0541c1d070c8

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="2309.17218") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D ReconstructionDescriptivePoint CloudsStereo Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction DTU ET-MVSNet Acc 0.329 #4 of 24 Archive leaderboard report
3D Reconstruction DTU ET-MVSNet Comp 0.253 #4 of 24 Archive leaderboard report
3D Reconstruction DTU ET-MVSNet Overall 0.291 #4 of 24 Archive leaderboard report
Point Clouds Tanks and Temples ET-MVSNet Mean F1 (Advanced) 40.41 #4 of 21 Archive leaderboard report
Point Clouds Tanks and Temples ET-MVSNet Mean F1 (Intermediate) 65.49 #4 of 21 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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