Papers › Unsupervised Monocular Depth Estimation with Left-Right Consistency

Unsupervised Monocular Depth Estimation with Left-Right Consistency

13 Sep 2016CVPR 2017 7arXiv:1609.03677archive 2025-07-28

Clément Godard, Oisin Mac Aodha, Gabriel J. Brostow

Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality depth data in a range of environments is a challenging problem. In this paper, we innovate beyond existing approaches, replacing the use of explicit depth data during training with easier-to-obtain binocular stereo footage. We propose a novel training objective that enables our convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data. Exploiting epipolar geometry constraints, we generate disparity images by training our network with an image reconstruction loss. We show that solving for image reconstruction alone results in poor quality depth images. To overcome this problem, we propose a novel training loss that enforces consistency between the disparities produced relative to both the left and right images, leading to improved performance and robustness compared to existing approaches. Our method produces state of the art results for monocular depth estimation on the KITTI driving dataset, even outperforming supervised methods that have been trained with ground truth depth.

PaperPDFConference PDFCodeCode Syntology ran

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 12 code samples harvested from 4 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 11 samples from 3 repositories, 7 ran (7 with no instrument failure; 0 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

16 repositories listed; official and paper-mentioned ones first.

mrharicot/monodepth officialmentioned in papermentioned on GitHubtfNOASSERTIONSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
IcarusWizard/monodepth-paddle mentioned on GitHubpaddleApache-2.0Syntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
Lebhoryi/learn_monodepth mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
OniroAI/MonoDepth-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
SharhadBashar/Depth-Percetion mentioned on GitHubpytorchSyntology: not harvested report
Yc174/monodepth mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
alwynmathew/monodepth-pytorch mentioned on GitHubpytorchSyntology: not harvested report
apllolulu/monodepth mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
iodncookie/my_loss_monodepth_master mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Digging Into Self-Supervised Monocular Depth Estimation (arXiv:1806.01260; that paper's own run record: 23 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 4 honoured, 1 violated, 8 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
janisgp/Sampling-free-Epistemic-Uncertainty mentioned on GitHubtfSyntology: not harvested report
muskie82/CNN-DSO mentioned on GitHubtfGPL-3.0Syntology: not harvested report
rickgroen/depthgan mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
tudelft/filled-disparity-monodepth mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
vinceecws/Monodepth mentioned on GitHubpytorchSyntology: not harvested report
vita-epfl/monoloco mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation (arXiv:1906.06059; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
xown3197/3D_Pedestrian_Localization_2021ComputerVision mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 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.

2ran · honoured contract
1ran; the contract check could not run
5ran
4unverified

Licence: 6 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

mrharicot/monodepth official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
post_process_disparity monodepth_main.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 92cb86f70b5d6123 · report fixture: signature disp:ndarray/3/float · returned ndarray · level recorded 2026-09-22
IcarusWizard/monodepth-paddle community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
compute_errors in 41 papers eval/evaluation_utils.py ran Apache-2.0 (permissive) · d83582de454a0b40 · report fixture: signature gt:ndarray/1/float, pred:ndarray/1/float · returned tuple · level recorded 2026-09-25
count_text_lines utils.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · bed135371a969180 · report fixture: signature file_path:str/0/str · returned int · level recorded 2026-09-22
gradient_x loss.py ran fingerprinted Apache-2.0 (permissive) · f98fd14e1515b523 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-26
gradient_y loss.py ran fingerprinted Apache-2.0 (permissive) · 7155e35b4a8e3f1d · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-26
load_gt_disp_kitti eval/evaluation_utils.py ran Apache-2.0 (permissive) · 6f8a54ff22b913e2 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
post_process_disparity utils.py ran fingerprinted Apache-2.0 (permissive) · 450c4a6f57ea4ed1 · report fixture: signature disp:ndarray/3/float · returned ndarray · level recorded 2026-09-26
convert_disps_to_depths_kitti eval/evaluation_utils.py unverified Apache-2.0 (permissive) · cf98eb3840092327 · report
Lebhoryi/learn_monodepth community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
count_text_lines monodepth_main.py ran · honoured contract licence not identified · pointer only · 914c9ab4e7b7469a · report fixture: signature file_path:str/0/str · returned int · level recorded 2026-09-22
rickgroen/depthgan community (archive-listed) 3 samples, 0 ran · 3 unverified
evaluate_cityscapes evaluate.py unverified no licence file found · pointer only · 4083ce7b80803fcd · report
evaluate_eigen evaluate.py unverified no licence file found · pointer only · 95194f001fcc993e · report
evaluate_kitti evaluate.py unverified no licence file found · pointer only · 557c80de93088f84 · report

Tasks

Depth EstimationDepth PredictionImage ReconstructionMonocular Depth EstimationUnsupervised Monocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split unsupervised Monodepth S absolute relative error 0.133 #54 of 55 Archive leaderboard report
Monocular Depth Estimation Mid-Air Dataset Monodepth Abs Rel 0.3136 #4 of 6 Archive leaderboard report
Monocular Depth Estimation Mid-Air Dataset Monodepth RMSE 13.595 #4 of 6 Archive leaderboard report
Monocular Depth Estimation Mid-Air Dataset Monodepth RMSE log 0.4380 #4 of 6 Archive leaderboard report
Monocular Depth Estimation Mid-Air Dataset Monodepth SQ Rel 8.7127 #4 of 6 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