{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/estimating-and-exploiting-the-aleatoric","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","arxiv_id":"2109.09881","date":"2021-09-20","proceeding":"ICCV 2021 10","authors":["Gwangbin Bae","Ignas Budvytis","Roberto Cipolla"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2109.09881v1","url_pdf":"https://arxiv.org/pdf/2109.09881v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"estimating-and-exploiting-the-aleatoric","repo_url":"https://github.com/baegwangbin/surface_normal_uncertainty","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"surface-normal-estimation","task_name":"Surface Normal Estimation"},{"task_slug":"surface-normals-estimation","task_name":"Surface Normals Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/surface-normals-estimation-on-nyu-depth-v2-1","task":"Surface Normals Estimation","dataset":"NYU Depth v2","model":"Bae et al.","rank_in_archive_order":4,"of":6,"metrics":{"% < 11.25":"62.2","% < 22.5":"79.3","% < 30":"85.2","Mean Angle Error":"14.9","RMSE":"23.5"},"uses_additional_data":false},{"leaderboard":"/sota/surface-normals-estimation-on-scannetv2","task":"Surface Normals Estimation","dataset":"ScanNetV2","model":"Bae et al.","rank_in_archive_order":2,"of":3,"metrics":{"% < 11.25":"71.1","% < 22.5":"85.4","% < 30":"89.8","Mean Angle Error":"11.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.09881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09881"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baegwangbin/surface_normal_uncertainty","reach":null}],"summary":{"ran":4,"ran_draft_wrong":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f091ebf994fa95e4","entry":"Conv2d","repo":"baegwangbin/surface_normal_uncertainty","repo_kind":"official","path":"models/submodules/decoder.py","file_url":"https://github.com/baegwangbin/surface_normal_uncertainty/blob/HEAD/models/submodules/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f091ebf994fa95e4"}},{"code_sha256_prefix":"27e80f3662d3f2c7","entry":"Decoder","repo":"baegwangbin/surface_normal_uncertainty","repo_kind":"official","path":"models/submodules/decoder.py","file_url":"https://github.com/baegwangbin/surface_normal_uncertainty/blob/HEAD/models/submodules/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"27e80f3662d3f2c7"}},{"code_sha256_prefix":"69c73add110c0082","entry":"UpSampleBN","repo":"baegwangbin/surface_normal_uncertainty","repo_kind":"official","path":"models/submodules/decoder.py","file_url":"https://github.com/baegwangbin/surface_normal_uncertainty/blob/HEAD/models/submodules/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69c73add110c0082"}},{"code_sha256_prefix":"6dc2273fb1df7171","entry":"UpSampleGN","repo":"baegwangbin/surface_normal_uncertainty","repo_kind":"official","path":"models/submodules/decoder.py","file_url":"https://github.com/baegwangbin/surface_normal_uncertainty/blob/HEAD/models/submodules/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dc2273fb1df7171"}},{"code_sha256_prefix":"4bb632c166c85093","entry":"norm_normalize","repo":"baegwangbin/surface_normal_uncertainty","repo_kind":"official","path":"models/submodules/decoder.py","file_url":"https://github.com/baegwangbin/surface_normal_uncertainty/blob/HEAD/models/submodules/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4bb632c166c85093"}},{"code_sha256_prefix":"d4f3f3f85d561675","entry":"sample_points","repo":"baegwangbin/surface_normal_uncertainty","repo_kind":"official","path":"models/submodules/decoder.py","file_url":"https://github.com/baegwangbin/surface_normal_uncertainty/blob/HEAD/models/submodules/decoder.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4f3f3f85d561675"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}