{"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/atlasnet-a-papier-mache-approach-to-learning","title":"AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation","arxiv_id":"1802.05384","date":"2018-02-15","proceeding":null,"authors":["Thibault Groueix","Matthew Fisher","Vladimir G. Kim","Bryan C. Russell","Mathieu Aubry"],"abstract":"We introduce a method for learning to generate the surface of 3D shapes. Our\napproach represents a 3D shape as a collection of parametric surface elements\nand, in contrast to methods generating voxel grids or point clouds, naturally\ninfers a surface representation of the shape. Beyond its novelty, our new shape\ngeneration framework, AtlasNet, comes with significant advantages, such as\nimproved precision and generalization capabilities, and the possibility to\ngenerate a shape of arbitrary resolution without memory issues. We demonstrate\nthese benefits and compare to strong baselines on the ShapeNet benchmark for\ntwo applications: (i) auto-encoding shapes, and (ii) single-view reconstruction\nfrom a still image. We also provide results showing its potential for other\napplications, such as morphing, parametrization, super-resolution, matching,\nand co-segmentation.","url_abs":"http://arxiv.org/abs/1802.05384v3","url_pdf":"http://arxiv.org/pdf/1802.05384v3.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":"atlasnet-a-papier-mache-approach-to-learning","repo_url":"https://github.com/ThibaultGROUEIX/AtlasNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"atlasnet-a-papier-mache-approach-to-learning","repo_url":"https://github.com/MChaus/NeoRender_test_task","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"atlasnet-a-papier-mache-approach-to-learning","repo_url":"https://github.com/gmum/LoCondA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-surface-generation","task_name":"3D Surface Generation"},{"task_slug":"point-cloud-completion","task_name":"Point Cloud Completion"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-shape-reconstruction-on-pix3d","task":"3D Shape Reconstruction","dataset":"Pix3D","model":"AtlasNet","rank_in_archive_order":5,"of":5,"metrics":{"CD":"0.125","EMD":"0.128","IoU":"N/A"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-completion-on-completion3d","task":"Point Cloud Completion","dataset":"Completion3D","model":"AtlasNet","rank_in_archive_order":4,"of":7,"metrics":{"Chamfer Distance":"17.77(?)"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1802.05384","atlas_url":"https://app.syntology.ai/?focus=1802.05384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05384"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/MChaus/NeoRender_test_task","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ThibaultGROUEIX/AtlasNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gmum/LoCondA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{},"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":3,"samples":[{"code_sha256_prefix":"61596a5e62b7bae5","entry":"add_gaussian_noise_to_pcloud","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"61596a5e62b7bae5"}},{"code_sha256_prefix":"2a8ccf1e9a2ca2b0","entry":"add_rotation_to_pcloud","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"2a8ccf1e9a2ca2b0"}},{"code_sha256_prefix":"8347bfc95350410c","entry":"rand_rotation_matrix","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"8347bfc95350410c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}