Papers › Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation

20 Sep 2021ICCV 2021 10arXiv:2109.09881archive 2025-07-28

Gwangbin Bae, Ignas Budvytis, Roberto Cipolla

Surface normal estimation from a single image is an important task in 3D scene understanding. In this paper, we address two limitations shared by the existing methods: the inability to estimate the aleatoric uncertainty and lack of detail in the prediction. The proposed network estimates the per-pixel surface normal probability distribution. We introduce a new parameterization for the distribution, such that its negative log-likelihood is the angular loss with learned attenuation. The expected value of the angular error is then used as a measure of the aleatoric uncertainty. We also present a novel decoder framework where pixel-wise multi-layer perceptrons are trained on a subset of pixels sampled based on the estimated uncertainty. The proposed uncertainty-guided sampling prevents the bias in training towards large planar surfaces and improves the quality of prediction, especially near object boundaries and on small structures. Experimental results show that the proposed method outperforms the state-of-the-art in ScanNet and NYUv2, and that the estimated uncertainty correlates well with the prediction error. Code is available at https://github.com/baegwangbin/surface_normal_uncertainty.

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="2109.09881")

Code

Syntology Ran 6 of 6 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

baegwangbin/surface_normal_uncertainty 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

6 samples harvested; 6 ran; 0 honoured the contract we drafted; 0 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 · our draft was wrong
1ran · fixture could not drive it
4ran

Licence: 0 of the 6 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 baegwangbin/surface_normal_uncertainty. “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.

Conv2d baegwangbin/surface_normal_uncertainty/models/submodules/decoder.py official repository ran fingerprinted MIT (permissive) · f091ebf994fa95e4 · report
Decoder baegwangbin/surface_normal_uncertainty/models/submodules/decoder.py official repository ran MIT (permissive) · 27e80f3662d3f2c7 · report
UpSampleBN baegwangbin/surface_normal_uncertainty/models/submodules/decoder.py official repository ran fingerprinted MIT (permissive) · 69c73add110c0082 · report
UpSampleGN baegwangbin/surface_normal_uncertainty/models/submodules/decoder.py official repository ran MIT (permissive) · 6dc2273fb1df7171 · report
norm_normalize baegwangbin/surface_normal_uncertainty/models/submodules/decoder.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 4bb632c166c85093 · report
sample_points baegwangbin/surface_normal_uncertainty/models/submodules/decoder.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · d4f3f3f85d561675 · report

Tasks

DecoderPredictionScene UnderstandingSurface Normal EstimationSurface Normals Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Surface Normals Estimation NYU Depth v2 Bae et al. % < 11.25 62.2 #4 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 Bae et al. % < 22.5 79.3 #4 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 Bae et al. % < 30 85.2 #4 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 Bae et al. Mean Angle Error 14.9 #4 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 Bae et al. RMSE 23.5 #4 of 6 Archive leaderboard report
Surface Normals Estimation ScanNetV2 Bae et al. % < 11.25 71.1 #2 of 3 Archive leaderboard report
Surface Normals Estimation ScanNetV2 Bae et al. % < 22.5 85.4 #2 of 3 Archive leaderboard report
Surface Normals Estimation ScanNetV2 Bae et al. % < 30 89.8 #2 of 3 Archive leaderboard report
Surface Normals Estimation ScanNetV2 Bae et al. Mean Angle Error 11.8 #2 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