{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/3d-jepa-a-joint-embedding-predictive","title":"3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning","arxiv_id":"2409.15803","date":"2024-09-24","proceeding":null,"authors":["Naiwen Hu","Haozhe Cheng","Yifan Xie","Shiqi Li","Jihua Zhu"],"abstract":"Invariance-based and generative methods have shown a conspicuous performance for 3D self-supervised representation learning (SSRL). However, the former relies on hand-crafted data augmentations that introduce bias not universally applicable to all downstream tasks, and the latter indiscriminately reconstructs masked regions, resulting in irrelevant details being saved in the representation space. To solve the problem above, we introduce 3D-JEPA, a novel non-generative 3D SSRL framework. Specifically, we propose a multi-block sampling strategy that produces a sufficiently informative context block and several representative target blocks. We present the context-aware decoder to enhance the reconstruction of the target blocks. Concretely, the context information is fed to the decoder continuously, facilitating the encoder in learning semantic modeling rather than memorizing the context information related to target blocks. Overall, 3D-JEPA predicts the representation of target blocks from a context block using the encoder and context-aware decoder architecture. Various downstream tasks on different datasets demonstrate 3D-JEPA's effectiveness and efficiency, achieving higher accuracy with fewer pretraining epochs, e.g., 88.65% accuracy on PB_T50_RS with 150 pretraining epochs.","url_abs":"https://arxiv.org/abs/2409.15803v1","url_pdf":"https://arxiv.org/pdf/2409.15803v1.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":[],"tasks":[{"task_slug":"3d-part-segmentation","task_name":"3D Part Segmentation"},{"task_slug":"3d-point-cloud-classification","task_name":"3D Point Cloud Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"few-shot-3d-point-cloud-classification","task_name":"Few-Shot 3D Point Cloud Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-part-segmentation-on-shapenet-part","task":"3D Part Segmentation","dataset":"ShapeNet-Part","model":"3D-JEPA","rank_in_archive_order":56,"of":67,"metrics":{"Class Average IoU":"86.41","Instance Average IoU":"84.93"},"uses_additional_data":true},{"leaderboard":"/sota/3d-point-cloud-classification-on-modelnet40","task":"3D Point Cloud Classification","dataset":"ModelNet40","model":"3D-JEPA","rank_in_archive_order":33,"of":111,"metrics":{"Overall Accuracy":"94.0"},"uses_additional_data":false},{"leaderboard":"/sota/3d-point-cloud-classification-on-scanobjectnn","task":"3D Point Cloud Classification","dataset":"ScanObjectNN","model":"3D-JEPA","rank_in_archive_order":24,"of":77,"metrics":{"OBJ-BG (OA)":"93.63","OBJ-ONLY (OA)":"94.49","Overall Accuracy":"89.52"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-3","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (10-shot)","model":"3D-JEPA","rank_in_archive_order":4,"of":31,"metrics":{"Overall Accuracy":"94.3","Standard Deviation":"3.6"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-4","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 10-way (20-shot)","model":"3D-JEPA","rank_in_archive_order":3,"of":31,"metrics":{"Overall Accuracy":"96.3","Standard Deviation":"2.4"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-1","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (10-shot)","model":"3D-JEPA","rank_in_archive_order":3,"of":30,"metrics":{"Overall Accuracy":"97.6","Standard Deviation":"2.0"},"uses_additional_data":true},{"leaderboard":"/sota/few-shot-3d-point-cloud-classification-on-2","task":"Few-Shot 3D Point Cloud Classification","dataset":"ModelNet40 5-way (20-shot)","model":"3D-JEPA","rank_in_archive_order":6,"of":30,"metrics":{"Overall Accuracy":"98.8","Standard Deviation":"0.4"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2409.15803","atlas_url":"https://app.syntology.ai/?focus=2409.15803","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2409.15803"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2409.15803\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2409.15803"},"call":"get_concepts_for_paper(arxiv_id=\"2409.15803\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"559170c5c168f96940381321c9cb19e1b0b3c5eee2708fef3d2c1c3f5809cb19","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}