{"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/pointr-diverse-point-cloud-completion-with","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","arxiv_id":"2108.08839","date":"2021-08-19","proceeding":"ICCV 2021 10","authors":["Xumin Yu","Yongming Rao","Ziyi Wang","Zuyan Liu","Jiwen Lu","Jie zhou"],"abstract":"Point clouds captured in real-world applications are often incomplete due to the limited sensor resolution, single viewpoint, and occlusion. Therefore, recovering the complete point clouds from partial ones becomes an indispensable task in many practical applications. In this paper, we present a new method that reformulates point cloud completion as a set-to-set translation problem and design a new model, called PoinTr that adopts a transformer encoder-decoder architecture for point cloud completion. By representing the point cloud as a set of unordered groups of points with position embeddings, we convert the point cloud to a sequence of point proxies and employ the transformers for point cloud generation. To facilitate transformers to better leverage the inductive bias about 3D geometric structures of point clouds, we further devise a geometry-aware block that models the local geometric relationships explicitly. The migration of transformers enables our model to better learn structural knowledge and preserve detailed information for point cloud completion. Furthermore, we propose two more challenging benchmarks with more diverse incomplete point clouds that can better reflect the real-world scenarios to promote future research. Experimental results show that our method outperforms state-of-the-art methods by a large margin on both the new benchmarks and the existing ones. Code is available at https://github.com/yuxumin/PoinTr","url_abs":"https://arxiv.org/abs/2108.08839v1","url_pdf":"https://arxiv.org/pdf/2108.08839v1.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":"pointr-diverse-point-cloud-completion-with","repo_url":"https://github.com/yuxumin/PoinTr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"point-cloud-completion","task_name":"Point Cloud Completion"},{"task_slug":"point-cloud-generation","task_name":"Point Cloud Generation"},{"task_slug":"single-view-3d-reconstruction","task_name":"Single-View 3D Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-completion-on-shapenet","task":"Point Cloud Completion","dataset":"ShapeNet","model":"PoinTr","rank_in_archive_order":10,"of":11,"metrics":{"Chamfer Distance L2":"8.38","F-Score@1%":"0.748"},"uses_additional_data":false},{"leaderboard":"/sota/single-view-3d-reconstruction-on-common","task":"Single-View 3D Reconstruction","dataset":"Common Objects in 3D","model":"PointTr","rank_in_archive_order":3,"of":3,"metrics":{"Avg. F1":"39.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2108.08839","atlas_url":"https://app.syntology.ai/?focus=2108.08839","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":"2108.08839"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2108.08839\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2108.08839"},"call":"get_concepts_for_paper(arxiv_id=\"2108.08839\")"}],"by_repo":[{"repo":"yuxumin/PoinTr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2301.04545"],"harvested_for_calls":[{"arxiv_id":"2301.04545","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2301.04545"},"call":"get_harvested_code_for_paper(arxiv_id=\"2301.04545\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d204d1ee3248f141c824f4a131a350e1af1bcebd3d5501c83d7ae637d398f58d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}