Papers › MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

10 Apr 2024CVPR 2024 1arXiv:2404.06842archive 2025-07-28

Ziyang Chen, Wei Long, He Yao, Yongjun Zhang, Bingshu Wang, Yongbin Qin, Jia Wu

Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at https://github.com/ZYangChen/MoCha-Stereo.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2404.06842")

Code

Syntology Ran 16 of 17 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 4 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 16 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zyangchen/mocha-stereo 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; 16 ran; 1 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
4ran · fixture could not drive it
9ran
1unverified

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 zyangchen/mocha-stereo. “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.

build_gwc_volume zyangchen/mocha-stereo/MoCha-Stereo/core/submodule.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · b2535abc79c55bba · report
conv1x1 zyangchen/mocha-stereo/MoCha-Stereo/nets/feature.py official repository ran MIT (permissive) · 8182b8e2a441abbd · report
conv2d zyangchen/mocha-stereo/MoCha-Stereo/nets/refinement.py official repository ran MIT (permissive) · 2c4f90d71c073dfe · report
conv3x3 zyangchen/mocha-stereo/MoCha-Stereo/nets/feature.py official repository ran MIT (permissive) · 9fba66e062846970 · report
conv5x5 zyangchen/mocha-stereo/MoCha-Stereo/nets/feature.py official repository ran MIT (permissive) · af5d1e93b7cc0884 · report
convbn zyangchen/mocha-stereo/MoCha-Stereo/core/extractor.py official repository ran · our draft was wrong MIT (permissive) · 15ab3c76823aef7e · report
count_parameters zyangchen/mocha-stereo/MoCha-Stereo/evaluate_stereo.py official repository ran · honoured contract MIT (permissive) · f6b944f50d3f15ae · report
default_conv zyangchen/mocha-stereo/MoCha-Stereo/nets/refinement.py official repository ran · our draft was wrong MIT (permissive) · 8b0e794d4d8f9b13 · report
disp_warp zyangchen/mocha-stereo/MoCha-Stereo/nets/warp.py official repository ran MIT (permissive) · 9797b88373fddbcd · report
groupwise_correlation zyangchen/mocha-stereo/MoCha-Stereo/core/submodule.py official repository ran · fixture could not drive it MIT (permissive) · 2e5c0e4dfa009847 · report
interp zyangchen/mocha-stereo/MoCha-Stereo/core/update.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 08bedbc0c0447f5d · report
meshgrid zyangchen/mocha-stereo/MoCha-Stereo/nets/warp.py official repository ran fingerprinted MIT (permissive) · d264efc1788f1659 · report
norm_correlation zyangchen/mocha-stereo/MoCha-Stereo/core/submodule.py official repository ran fingerprinted MIT (permissive) · 7d2e52593158ea33 · report
normalize_coords zyangchen/mocha-stereo/MoCha-Stereo/nets/warp.py official repository ran MIT (permissive) · 62da485d08a1a205 · report
pool2x zyangchen/mocha-stereo/MoCha-Stereo/core/update.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 25894ad2a73a8142 · report
weight zyangchen/mocha-stereo/MoCha-Stereo/nets/mogrifier.py official repository ran MIT (permissive) · 3ea274451c800fdf · report
pool4x zyangchen/mocha-stereo/MoCha-Stereo/core/update.py official repository unverified MIT (permissive) · 771e8ac695af28a9 · report

Tasks

Disparity EstimationStereo Depth EstimationStereo Disparity EstimationStereo Matching

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Stereo Depth Estimation KITTI 2015 MoCha-Stereo D1-all All 1.53 #1 of 2 Archive leaderboard report
Stereo Depth Estimation KITTI 2015 MoCha-Stereo D1-all Noc 1.44 #1 of 2 Archive leaderboard report
Stereo Disparity Estimation KITTI 2015 MoCha-Stereo D1-all 1.53 #1 of 2 Archive leaderboard report
Stereo Disparity Estimation Middlebury 2014 MoCha-V2 D1 Error (2px) 3.51 #1 of 2 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.

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