Papers › Unsupervised Scale-consistent Depth Learning from Video

Unsupervised Scale-consistent Depth Learning from Video

25 May 2021arXiv:2105.11610archive 2025-07-28

Jia-Wang Bian, Huangying Zhan, Naiyan Wang, Zhichao Li, Le Zhang, Chunhua Shen, Ming-Ming Cheng, Ian Reid

We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training and enables the scale-consistent prediction at inference time. Our contributions include: (i) we propose a geometry consistency loss, which penalizes the inconsistency of predicted depths between adjacent views; (ii) we propose a self-discovered mask to automatically localize moving objects that violate the underlying static scene assumption and cause noisy signals during training; (iii) we demonstrate the efficacy of each component with a detailed ablation study and show high-quality depth estimation results in both KITTI and NYUv2 datasets. Moreover, thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system for more robust and accurate tracking. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training. Finally, we provide several demos for qualitative evaluation.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

JiawangBian/sc_depth_pl officialpytorchGPL-3.0Syntology: not harvested report
JiawangBian/SC-SfMLearner-Release pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video (arXiv:1908.10553; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth EstimationMonocular Depth EstimationMonocular Visual OdometrySimultaneous Localization and Mapping

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet 50) Delta < 1.25 0.873 #65 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet 50) Delta < 1.25^2 0.960 #65 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet 50) Delta < 1.25^3 0.982 #65 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet 50) RMSE 4.706 #65 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet 50) RMSE log 0.191 #65 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet 50) absolute relative error 0.114 #65 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet18) Delta < 1.25 0.863 #67 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet18) Delta < 1.25^2 0.957 #67 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet18) Delta < 1.25^3 0.981 #67 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet18) RMSE 4.950 #67 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet18) RMSE log 0.197 #67 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split SC-Depth (ResNet18) absolute relative error 0.119 #67 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised Bian et al Absolute relative error (AbsRel) 0.157 #6 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised Bian et al Root mean square error (RMSE) 0.593 #6 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised Bian et al delta_1 78.0 #6 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised Bian et al delta_2 94.0 #6 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised Bian et al delta_3 98.4 #6 of 8 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