Papers › IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty

7 Oct 2022arXiv:2210.03676archive 2025-07-28

Gwangbin Bae, Ignas Budvytis, Roberto Cipolla

Single image surface normal estimation and depth estimation are closely related problems as the former can be calculated from the latter. However, the surface normals computed from the output of depth estimation methods are significantly less accurate than the surface normals directly estimated by networks. To reduce such discrepancy, we introduce a novel framework that uses surface normal and its uncertainty to recurrently refine the predicted depth-map. The depth of each pixel can be propagated to a query pixel, using the predicted surface normal as guidance. We thus formulate depth refinement as a classification of choosing the neighboring pixel to propagate from. Then, by propagating to sub-pixel points, we upsample the refined, low-resolution output. The proposed method shows state-of-the-art performance on NYUv2 and iBims-1 - both in terms of depth and normal. Our refinement module can also be attached to the existing depth estimation methods to improve their accuracy. We also show that our framework, only trained for depth estimation, can also be used for depth completion. The code is available at https://github.com/baegwangbin/IronDepth.

PaperPDFCode

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

Code

baegwangbin/irondepth officialmentioned in papermentioned 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

Monocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation NYU-Depth V2 IronDepth Delta < 1.25 0.910 #51 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 IronDepth Delta < 1.25^2 0.985 #51 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 IronDepth Delta < 1.25^3 0.997 #51 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 IronDepth RMSE 0.352 #51 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 IronDepth absolute relative error 0.101 #51 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 IronDepth log 10 0.043 #51 of 85 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