{"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/cuboids-revisited-learning-robust-3d-shape","title":"Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images","arxiv_id":"2105.02047","date":"2021-05-05","proceeding":"CVPR 2021 1","authors":["Florian Kluger","Hanno Ackermann","Eric Brachmann","Michael Ying Yang","Bodo Rosenhahn"],"abstract":"Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring these primitives is an important step to attain high-level, abstract scene descriptions. Previous approaches directly estimate shape parameters from a 2D or 3D input, and are only able to reproduce simple objects, yet unable to accurately parse more complex 3D scenes. In contrast, we propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map. We condition the network on previously detected parts of the scene, thus parsing it one-by-one. To obtain 3D features from a single RGB image, we additionally optimise a feature extraction CNN in an end-to-end manner. However, naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene behind. We thus propose an occlusion-aware distance metric correctly handling opaque scenes. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the challenging NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.","url_abs":"https://arxiv.org/abs/2105.02047v1","url_pdf":"https://arxiv.org/pdf/2105.02047v1.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":"cuboids-revisited-learning-robust-3d-shape","repo_url":"https://github.com/fkluger/cuboids_revisited","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.02047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.02047"}},"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/fkluger/cuboids_revisited","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_violates":1,"unverified":12},"by_repo_kind":{"official":{"samples":13,"ran":1,"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":"eb7801586aa2560a","entry":"rgb2gray","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"datasets/smh.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/datasets/smh.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"eb7801586aa2560a"}},{"code_sha256_prefix":"34820b208495b44c","entry":"cuboid_mesh","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"datasets/synthetic_cuboids.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/datasets/synthetic_cuboids.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"34820b208495b44c"}},{"code_sha256_prefix":"40ed722d7c0a8379","entry":"e_step","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/em_algorithm.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/em_algorithm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"40ed722d7c0a8379"}},{"code_sha256_prefix":"c90770b4d4fe58ba","entry":"estimate_planes","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/fitting.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/fitting.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c90770b4d4fe58ba"}},{"code_sha256_prefix":"f1547b350abc7741","entry":"fexp","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/equal_distance_sampler_sq.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/equal_distance_sampler_sq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"f1547b350abc7741"}},{"code_sha256_prefix":"7c81a4c434f45a23","entry":"manual_jacobian_p","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"networks/layers.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/networks/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7c81a4c434f45a23"}},{"code_sha256_prefix":"2ae614a668daf19f","entry":"manual_jacobian_x","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"networks/layers.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/networks/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2ae614a668daf19f"}},{"code_sha256_prefix":"6a85549fd5684f82","entry":"sample_spherical","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"datasets/synthetic_cuboids.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/datasets/synthetic_cuboids.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6a85549fd5684f82"}},{"code_sha256_prefix":"78bb52ae71e528a9","entry":"sigmoid","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/consistency.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/consistency.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"78bb52ae71e528a9"}},{"code_sha256_prefix":"13e6282360f1c5bb","entry":"sigmoid_","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/consistency.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/consistency.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"13e6282360f1c5bb"}},{"code_sha256_prefix":"00b04bc234d801ff","entry":"soft_inlier_fun_gen","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/consistency.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/consistency.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"00b04bc234d801ff"}},{"code_sha256_prefix":"ebb6838ea65260c2","entry":"sq_surface","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"util/equal_distance_sampler_sq.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/util/equal_distance_sampler_sq.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ebb6838ea65260c2"}},{"code_sha256_prefix":"13a01a6a29372a67","entry":"twist_to_matrix","repo":"fkluger/cuboids_revisited","repo_kind":"official","path":"networks/pose_net.py","file_url":"https://github.com/fkluger/cuboids_revisited/blob/HEAD/networks/pose_net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"13a01a6a29372a67"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}