{"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/unsupervised-3d-learning-for-shape-analysis","title":"Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination","arxiv_id":"2008.01068","date":"2020-08-03","proceeding":null,"authors":["Peng-Shuai Wang","Yu-Qi Yang","Qian-Fang Zou","Zhirong Wu","Yang Liu","Xin Tong"],"abstract":"Although unsupervised feature learning has demonstrated its advantages to reducing the workload of data labeling and network design in many fields, existing unsupervised 3D learning methods still cannot offer a generic network for various shape analysis tasks with competitive performance to supervised methods. In this paper, we propose an unsupervised method for learning a generic and efficient shape encoding network for different shape analysis tasks. The key idea of our method is to jointly encode and learn shape and point features from unlabeled 3D point clouds. For this purpose, we adapt HR-Net to octree-based convolutional neural networks for jointly encoding shape and point features with fused multiresolution subnetworks and design a simple-yet-efficient Multiresolution Instance Discrimination (MID) loss for jointly learning the shape and point features. Our network takes a 3D point cloud as input and output both shape and point features. After training, the network is concatenated with simple task-specific back-end layers and fine-tuned for different shape analysis tasks. We evaluate the efficacy and generality of our method and validate our network and loss design with a set of shape analysis tasks, including shape classification, semantic shape segmentation, as well as shape registration tasks. With simple back-ends, our network demonstrates the best performance among all unsupervised methods and achieves competitive performance to supervised methods, especially in tasks with a small labeled dataset. For fine-grained shape segmentation, our method even surpasses existing supervised methods by a large margin.","url_abs":"https://arxiv.org/abs/2008.01068v2","url_pdf":"https://arxiv.org/pdf/2008.01068v2.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":"unsupervised-3d-learning-for-shape-analysis","repo_url":"https://github.com/Microsoft/O-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-point-cloud-linear-classification","task_name":"3D Point Cloud Linear Classification"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-point-cloud-linear-classification-on","task":"3D Point Cloud Linear Classification","dataset":"ModelNet40","model":"MID-FC","rank_in_archive_order":14,"of":20,"metrics":{"Overall Accuracy":"90.3"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-segmentation-on-partnet","task":"3D Semantic Segmentation","dataset":"PartNet","model":"MID-Net","rank_in_archive_order":2,"of":6,"metrics":{"mIOU":"60.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.01068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.01068"}},"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/Microsoft/O-CNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"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":"33c8859edabefe8e","entry":"branch","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_hrnet.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_hrnet.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":"33c8859edabefe8e"}},{"code_sha256_prefix":"f2dc23962695d2b5","entry":"branches","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_hrnet.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_hrnet.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":"f2dc23962695d2b5"}},{"code_sha256_prefix":"2d88271666e60392","entry":"cls_network","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_cls.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_cls.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":"2d88271666e60392"}},{"code_sha256_prefix":"9771607aa9495cf5","entry":"get_input_signal","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_completion.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_completion.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":"9771607aa9495cf5"}},{"code_sha256_prefix":"26fdcaa081b14291","entry":"get_split_label","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_completion.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_completion.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":"26fdcaa081b14291"}},{"code_sha256_prefix":"a118ef8b9502a8ce","entry":"make_autoencoder","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_ae.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_ae.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":"a118ef8b9502a8ce"}},{"code_sha256_prefix":"e38b3343da083701","entry":"network_ocnn","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_cls.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_cls.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":"e38b3343da083701"}},{"code_sha256_prefix":"37dc89159ef62b72","entry":"network_resnet","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_cls.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_cls.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":"37dc89159ef62b72"}},{"code_sha256_prefix":"4ea8008f161405ca","entry":"trans_func","repo":"Microsoft/O-CNN","repo_kind":"listed","path":"tensorflow/script/network_hrnet.py","file_url":"https://github.com/Microsoft/O-CNN/blob/HEAD/tensorflow/script/network_hrnet.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":"4ea8008f161405ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}