{"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-implicit-moving-least-squares-functions","title":"Deep Implicit Moving Least-Squares Functions for 3D Reconstruction","arxiv_id":"2103.12266","date":"2021-03-23","proceeding":"CVPR 2021 1","authors":["Shi-Lin Liu","Hao-Xiang Guo","Hao Pan","Peng-Shuai Wang","Xin Tong","Yang Liu"],"abstract":"Point set is a flexible and lightweight representation widely used for 3D deep learning. However, their discrete nature prevents them from representing continuous and fine geometry, posing a major issue for learning-based shape generation. In this work, we turn the discrete point sets into smooth surfaces by introducing the well-known implicit moving least-squares (IMLS) surface formulation, which naturally defines locally implicit functions on point sets. We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces. Our IMLSNet predicts an octree structure as a scaffold for generating MLS points where needed and characterizes shape geometry with learned local priors. Furthermore, our implicit function evaluation is independent of the neural network once the MLS points are predicted, thus enabling fast runtime evaluation. Our experiments on 3D object reconstruction demonstrate that IMLSNets outperform state-of-the-art learning-based methods in terms of reconstruction quality and computational efficiency. Extensive ablation tests also validate our network design and loss functions.","url_abs":"https://arxiv.org/abs/2103.12266v2","url_pdf":"https://arxiv.org/pdf/2103.12266v2.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-implicit-moving-least-squares-functions","repo_url":"https://github.com/Andy97/DeepMLS","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-object-reconstruction","task_name":"3D Object Reconstruction"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"object-reconstruction","task_name":"Object Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.12266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12266"}},"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":"deterministic:regex_extraction","url":"https://github.com/Andy97/DeepMLS","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":14},"by_repo_kind":{"official":{"samples":14,"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":"6b9c5e67950491d0","entry":"DoubleList_to_Bytes","repo":"Andy97/DeepMLS","repo_kind":"official","path":"points3d-tf/pointsdataset/points_dataset_octreed7.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/points3d-tf/pointsdataset/points_dataset_octreed7.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":"6b9c5e67950491d0"}},{"code_sha256_prefix":"cfa1ab3b87f65878","entry":"Float32List_to_Bytes","repo":"Andy97/DeepMLS","repo_kind":"official","path":"points3d-tf/pointsdataset/points_dataset_octreed7.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/points3d-tf/pointsdataset/points_dataset_octreed7.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":"cfa1ab3b87f65878"}},{"code_sha256_prefix":"135b89fc9605f85a","entry":"IntList_to_Bytes","repo":"Andy97/DeepMLS","repo_kind":"official","path":"points3d-tf/pointsdataset/points_dataset_octreed7.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/points3d-tf/pointsdataset/points_dataset_octreed7.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":"135b89fc9605f85a"}},{"code_sha256_prefix":"22b0391dbc9591fe","entry":"average_gradient","repo":"Andy97/DeepMLS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Andy97/DeepMLS/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":"22b0391dbc9591fe"}},{"code_sha256_prefix":"489c5f27ae7ac730","entry":"batch_norm","repo":"Andy97/DeepMLS","repo_kind":"official","path":"Octree/ocnn.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/Octree/ocnn.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":"489c5f27ae7ac730"}},{"code_sha256_prefix":"259c9e2644534d0b","entry":"config_reader","repo":"Andy97/DeepMLS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Andy97/DeepMLS/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":"259c9e2644534d0b"}},{"code_sha256_prefix":"025d5ba4076f4507","entry":"dense","repo":"Andy97/DeepMLS","repo_kind":"official","path":"Octree/ocnn.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/Octree/ocnn.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":"025d5ba4076f4507"}},{"code_sha256_prefix":"81a82eb551047ed3","entry":"get_variables_with_name","repo":"Andy97/DeepMLS","repo_kind":"official","path":"Octree/ocnn.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/Octree/ocnn.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":"81a82eb551047ed3"}},{"code_sha256_prefix":"527c707a39fdee51","entry":"normal_unit_norm_regularization","repo":"Andy97/DeepMLS","repo_kind":"official","path":"DeepMLS_Generation.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/DeepMLS_Generation.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":"527c707a39fdee51"}},{"code_sha256_prefix":"13007f9c486275fe","entry":"octree_network_unet","repo":"Andy97/DeepMLS","repo_kind":"official","path":"network_architecture.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/network_architecture.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":"13007f9c486275fe"}},{"code_sha256_prefix":"01460b3f669373ad","entry":"octree_network_unet_completion_decode_shape","repo":"Andy97/DeepMLS","repo_kind":"official","path":"network_architecture.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/network_architecture.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":"01460b3f669373ad"}},{"code_sha256_prefix":"84287e86ee7c75a5","entry":"preprocess_octree_data_from_unoriented_points","repo":"Andy97/DeepMLS","repo_kind":"official","path":"network_architecture.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/network_architecture.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":"84287e86ee7c75a5"}},{"code_sha256_prefix":"1767f3533c90fc34","entry":"rowwise_l2_norm_squared","repo":"Andy97/DeepMLS","repo_kind":"official","path":"mls_marching_cubes.py","file_url":"https://github.com/Andy97/DeepMLS/blob/HEAD/mls_marching_cubes.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":"1767f3533c90fc34"}},{"code_sha256_prefix":"1a5ed5d936a5d8c3","entry":"tf_summary_from_dict","repo":"Andy97/DeepMLS","repo_kind":"official","path":"utils.py","file_url":"https://github.com/Andy97/DeepMLS/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":"1a5ed5d936a5d8c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}