{"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/learning-free-form-deformations-for-3d-object","title":"Learning Free-Form Deformations for 3D Object Reconstruction","arxiv_id":"1803.10932","date":"2018-03-29","proceeding":null,"authors":["Dominic Jack","Jhony K. Pontes","Sridha Sridharan","Clinton Fookes","Sareh Shirazi","Frederic Maire","Anders Eriksson"],"abstract":"Representing 3D shape in deep learning frameworks in an accurate, efficient\nand compact manner still remains an open challenge. Most existing work\naddresses this issue by employing voxel-based representations. While these\napproaches benefit greatly from advances in computer vision by generalizing 2D\nconvolutions to the 3D setting, they also have several considerable drawbacks.\nThe computational complexity of voxel-encodings grows cubically with the\nresolution thus limiting such representations to low-resolution 3D\nreconstruction. In an attempt to solve this problem, point cloud\nrepresentations have been proposed. Although point clouds are more efficient\nthan voxel representations as they only cover surfaces rather than volumes,\nthey do not encode detailed geometric information about relationships between\npoints. In this paper we propose a method to learn free-form deformations (FFD)\nfor the task of 3D reconstruction from a single image. By learning to deform\npoints sampled from a high-quality mesh, our trained model can be used to\nproduce arbitrarily dense point clouds or meshes with fine-grained geometry. We\nevaluate our proposed framework on both synthetic and real-world data and\nachieve state-of-the-art results on point-cloud and volumetric metrics.\nAdditionally, we qualitatively demonstrate its applicability to label\ntransferring for 3D semantic segmentation.","url_abs":"http://arxiv.org/abs/1803.10932v1","url_pdf":"http://arxiv.org/pdf/1803.10932v1.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":"learning-free-form-deformations-for-3d-object","repo_url":"https://github.com/jackd/template_ffd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"3d-object-reconstruction","task_name":"3D Object Reconstruction"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"form","task_name":"Form"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-reconstruction","task_name":"Object Reconstruction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.10932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.10932"}},"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/jackd/template_ffd","reach":null}],"summary":{"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"dda33101a28750d2","entry":"get_centroids","repo":"jackd/template_ffd","repo_kind":"official","path":"model/template_ffd_builder.py","file_url":"https://github.com/jackd/template_ffd/blob/HEAD/model/template_ffd_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dda33101a28750d2"}},{"code_sha256_prefix":"5a7767cfeceb82b5","entry":"get_nn","repo":"jackd/template_ffd","repo_kind":"official","path":"model/template_ffd_builder.py","file_url":"https://github.com/jackd/template_ffd/blob/HEAD/model/template_ffd_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a7767cfeceb82b5"}},{"code_sha256_prefix":"a6a367d6cbb99241","entry":"segment_faces","repo":"jackd/template_ffd","repo_kind":"official","path":"model/template_ffd_builder.py","file_url":"https://github.com/jackd/template_ffd/blob/HEAD/model/template_ffd_builder.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a6a367d6cbb99241"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}