Papers › Wasserstein Distances for Stereo Disparity Estimation

Wasserstein Distances for Stereo Disparity Estimation

6 Jul 2020NeurIPS 2020 12arXiv:2007.03085archive 2025-07-28

Divyansh Garg, Yan Wang, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger, Wei-Lun Chao

Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values. This leads to inaccurate results when the true depth or disparity does not match any of these values. The fact that this distribution is usually learned indirectly through a regression loss causes further problems in ambiguous regions around object boundaries. We address these issues using a new neural network architecture that is capable of outputting arbitrary depth values, and a new loss function that is derived from the Wasserstein distance between the true and the predicted distributions. We validate our approach on a variety of tasks, including stereo disparity and depth estimation, and the downstream 3D object detection. Our approach drastically reduces the error in ambiguous regions, especially around object boundaries that greatly affect the localization of objects in 3D, achieving the state-of-the-art in 3D object detection for autonomous driving. Our code will be available at https://github.com/Div99/W-Stereo-Disp.

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="2007.03085")

Code

Syntology Ran 2 of 9 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Div99/W-Stereo-Disp 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

9 samples harvested; 2 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.

1ran · violated contract
1ran
7unverified

Licence: 0 of the 9 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 Div99/W-Stereo-Disp. “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.

default_loader Div99/W-Stereo-Disp/src/disp_dataloader/KITTILoader_dataset3d.py official repository ran MIT (permissive) · ac269a0e4b8d946e · report
is_image_file Div99/W-Stereo-Disp/src/disp_dataloader/KITTILoader3D.py official repository ran · violated contract MIT (permissive) · ab4109634b75ef8b · report
dataloader Div99/W-Stereo-Disp/src/disp_dataloader/KITTILoader3D.py official repository unverified MIT (permissive) · 74a08f63b12add42 · report
default_loader Div99/W-Stereo-Disp/src/disp_dataloader/SceneFlowLoader.py official repository unverified MIT (permissive) · 0b3ce8456d675a8c · report
disparity_loader Div99/W-Stereo-Disp/src/disp_dataloader/KITTILoader_dataset3d.py official repository unverified MIT (permissive) · 8d9f5f6ce951aa15 · report
disparity_loader Div99/W-Stereo-Disp/src/disp_dataloader/SceneFlowLoader.py official repository unverified MIT (permissive) · aaf877e27c4a3c3e · report
dynamic_baseline Div99/W-Stereo-Disp/src/disp_dataloader/KITTI_submission_loader.py official repository unverified MIT (permissive) · b9ee501ff15b4629 · report
readPFM Div99/W-Stereo-Disp/src/disp_dataloader/readpfm.py official repository unverified MIT (permissive) · aaea02c311c902eb · report
read_calib_file Div99/W-Stereo-Disp/src/disp_dataloader/KITTI_submission_loader.py official repository unverified MIT (permissive) · e18b9288494dc86a · report

Tasks

3D Object Detection3D Object Detection From Stereo ImagesAutonomous DrivingDepth EstimationDisparity EstimationObjectObject DetectionStereo Depth EstimationStereo Disparity Estimationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection From Stereo Images KITTI Cars Moderate CDN-DSGN AP75 54.2 #3 of 12 Archive leaderboard report
Stereo Depth Estimation KITTI2015 CDN-GANet Deep three pixel error 1.92 #3 of 7 Archive leaderboard report
Stereo Disparity Estimation Scene Flow CDN-GANet Deep EPE 0.7 #4 of 7 Archive leaderboard report
Stereo Disparity Estimation Scene Flow CDN-GANet Deep one pixel error 7.7 #4 of 7 Archive leaderboard report
Stereo Disparity Estimation Scene Flow CDN-GANet Deep three pixel error 2.98 #4 of 7 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