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 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="2309.17218")

Code

Syntology Ran 5 of 13 code samples harvested from 1 repository linked to this paper; 8 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

tqtqliu/et-mvsnet 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

13 samples harvested; 5 ran; 0 honoured the contract we drafted; 8 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.

2ran · our draft was wrong
3ran
8unverified

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. “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.

MVS4net_loss tqtqliu/et-mvsnet/models/MVS4Net.py official repository ran MIT (permissive) · 9c73a828f8730bcc · report
init_inverse_range tqtqliu/et-mvsnet/models/module.py official repository ran · our draft was wrong MIT (permissive) · 9dc0b1027a30eb55 · report
init_range tqtqliu/et-mvsnet/models/module.py official repository ran · our draft was wrong MIT (permissive) · c72a4a2293997c31 · report
make_nograd_func tqtqliu/et-mvsnet/utils.py official repository ran MIT (permissive) · a76fc7fb6958f97c · report
make_recursive_func tqtqliu/et-mvsnet/utils.py official repository ran MIT (permissive) · b62bec09ceeaca79 · report
Blend_loss tqtqliu/et-mvsnet/models/MVS4Net.py official repository unverified MIT (permissive) · 46e1be8739ffd15e · report
MVS4net TQTQliu/ET-MVSNet/models/MVS4Net.py official repository unverified MIT (permissive) · 683e0541c1d070c8 · report
cross_entropy_loss tqtqliu/et-mvsnet/models/MVS4Net.py official repository unverified MIT (permissive) · 41f59aee24980c21 · report
homo_warping tqtqliu/et-mvsnet/models/module.py official repository unverified MIT (permissive) · 2433e10d0340ac47 · report
read_pfm tqtqliu/et-mvsnet/datasets/data_io.py official repository unverified MIT (permissive) · 6b687b02c05fe850 · report
tensor2float tqtqliu/et-mvsnet/utils.py official repository unverified MIT (permissive) · 8e28f96374f1b285 · report
train_sample tqtqliu/et-mvsnet/train_bld.py official repository unverified MIT (permissive) · acee5a023ac9e377 · report
train_sample tqtqliu/et-mvsnet/train_dtu.py official repository unverified MIT (permissive) · b6e60e102b3e750e · report

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