Papers › Toward Practical Monocular Indoor Depth Estimation

Toward Practical Monocular Indoor Depth Estimation

4 Dec 2021CVPR 2022 1arXiv:2112.02306archive 2025-07-28

Cho-Ying Wu, Jialiang Wang, Michael Hall, Ulrich Neumann, Shuochen Su

The majority of prior monocular depth estimation methods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we propose a structure distillation approach to learn knacks from an off-the-shelf relative depth estimator that produces structured but metric-agnostic depth. By combining structure distillation with a branch that learns metrics from left-right consistency, we attain structured and metric depth for generic indoor scenes and make inferences in real-time. To facilitate learning and evaluation, we collect SimSIN, a dataset from simulation with thousands of environments, and UniSIN, a dataset that contains about 500 real scan sequences of generic indoor environments. We experiment in both sim-to-real and real-to-real settings, and show improvements, as well as in downstream applications using our depth maps. This work provides a full study, covering methods, data, and applications aspects.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

facebookresearch/DistDepth officialmentioned on GitHubpytorchNOASSERTION report
cake-lab/Mobile-AR-Depth-Estimation mentioned on GitHubpytorch 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

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

Tasks

Depth EstimationMonocular Depth Estimation

Datasets

Introduced by this paper, per the archive.

VA (Virtual Apartment)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation NYU-Depth V2 self-supervised DistDepth Absolute relative error (AbsRel) 0.130 #2 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised DistDepth Root mean square error (RMSE) 0.517 #2 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised DistDepth delta_1 83.2 #2 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised DistDepth delta_2 96.3 #2 of 8 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 self-supervised DistDepth delta_3 99.0 #2 of 8 Archive leaderboard report
Monocular Depth Estimation VA (Virtual Apartment) DistDepth Absolute relative error (AbsRel) 0.175 #1 of 3 Archive leaderboard report
Monocular Depth Estimation VA (Virtual Apartment) DistDepth Log root mean square error (RMSE_log) 0.213 #1 of 3 Archive leaderboard report
Monocular Depth Estimation VA (Virtual Apartment) DistDepth Mean average error (MAE) 0.253 #1 of 3 Archive leaderboard report
Monocular Depth Estimation VA (Virtual Apartment) DistDepth Root mean square error (RMSE) 0.374 #1 of 3 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