{"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/deep-geometric-prior-for-surface","title":"Deep Geometric Prior for Surface Reconstruction","arxiv_id":"1811.10943","date":"2018-11-27","proceeding":"CVPR 2019 6","authors":["Francis Williams","Teseo Schneider","Claudio Silva","Denis Zorin","Joan Bruna","Daniele Panozzo"],"abstract":"The reconstruction of a discrete surface from a point cloud is a fundamental\ngeometry processing problem that has been studied for decades, with many\nmethods developed. We propose the use of a deep neural network as a geometric\nprior for surface reconstruction. Specifically, we overfit a neural network\nrepresenting a local chart parameterization to part of an input point cloud\nusing the Wasserstein distance as a measure of approximation. By jointly\nfitting many such networks to overlapping parts of the point cloud, while\nenforcing a consistency condition, we compute a manifold atlas. By sampling\nthis atlas, we can produce a dense reconstruction of the surface approximating\nthe input cloud. The entire procedure does not require any training data or\nexplicit regularization, yet, we show that it is able to perform remarkably\nwell: not introducing typical overfitting artifacts, and approximating sharp\nfeatures closely at the same time. We experimentally show that this geometric\nprior produces good results for both man-made objects containing sharp features\nand smoother organic objects, as well as noisy inputs. We compare our method\nwith a number of well-known reconstruction methods on a standard surface\nreconstruction benchmark.","url_abs":"http://arxiv.org/abs/1811.10943v2","url_pdf":"http://arxiv.org/pdf/1811.10943v2.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":"deep-geometric-prior-for-surface","repo_url":"https://github.com/fwilliams/deep-geometric-prior","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10943"}},"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/fwilliams/deep-geometric-prior","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"854ccec0a1a14888","entry":"meshgrid_face_indices","repo":"fwilliams/deep-geometric-prior","repo_kind":"official","path":"utils.py","file_url":"https://github.com/fwilliams/deep-geometric-prior/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"854ccec0a1a14888"}},{"code_sha256_prefix":"9d1661ef3ce235d2","entry":"meshgrid_from_lloyd_ts","repo":"fwilliams/deep-geometric-prior","repo_kind":"official","path":"utils.py","file_url":"https://github.com/fwilliams/deep-geometric-prior/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d1661ef3ce235d2"}},{"code_sha256_prefix":"265a419c190b5b07","entry":"meshgrid_vertices","repo":"fwilliams/deep-geometric-prior","repo_kind":"official","path":"utils.py","file_url":"https://github.com/fwilliams/deep-geometric-prior/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"265a419c190b5b07"}},{"code_sha256_prefix":"2fafb26af6e6905d","entry":"patch_means","repo":"fwilliams/deep-geometric-prior","repo_kind":"official","path":"reconstruct_surface.py","file_url":"https://github.com/fwilliams/deep-geometric-prior/blob/HEAD/reconstruct_surface.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2fafb26af6e6905d"}},{"code_sha256_prefix":"2c406d16611ebd44","entry":"transform_pointcloud","repo":"fwilliams/deep-geometric-prior","repo_kind":"official","path":"reconstruct_single_patch.py","file_url":"https://github.com/fwilliams/deep-geometric-prior/blob/HEAD/reconstruct_single_patch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c406d16611ebd44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}