{"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/lion-latent-point-diffusion-models-for-3d","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","arxiv_id":"2210.06978","date":"2022-10-12","proceeding":null,"authors":["Xiaohui Zeng","Arash Vahdat","Francis Williams","Zan Gojcic","Or Litany","Sanja Fidler","Karsten Kreis"],"abstract":"Denoising diffusion models (DDMs) have shown promising results in 3D point cloud synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high generation quality, (ii) flexibility for manipulation and applications such as conditional synthesis and shape interpolation, and (iii) the ability to output smooth surfaces or meshes. To this end, we introduce the hierarchical Latent Point Diffusion Model (LION) for 3D shape generation. LION is set up as a variational autoencoder (VAE) with a hierarchical latent space that combines a global shape latent representation with a point-structured latent space. For generation, we train two hierarchical DDMs in these latent spaces. The hierarchical VAE approach boosts performance compared to DDMs that operate on point clouds directly, while the point-structured latents are still ideally suited for DDM-based modeling. Experimentally, LION achieves state-of-the-art generation performance on multiple ShapeNet benchmarks. Furthermore, our VAE framework allows us to easily use LION for different relevant tasks: LION excels at multimodal shape denoising and voxel-conditioned synthesis, and it can be adapted for text- and image-driven 3D generation. We also demonstrate shape autoencoding and latent shape interpolation, and we augment LION with modern surface reconstruction techniques to generate smooth 3D meshes. We hope that LION provides a powerful tool for artists working with 3D shapes due to its high-quality generation, flexibility, and surface reconstruction. Project page and code: https://nv-tlabs.github.io/LION.","url_abs":"https://arxiv.org/abs/2210.06978v1","url_pdf":"https://arxiv.org/pdf/2210.06978v1.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":"lion-latent-point-diffusion-models-for-3d","repo_url":"https://github.com/nv-tlabs/LION","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"lion-latent-point-diffusion-models-for-3d","repo_url":"https://github.com/MS-Mind/MS-Code-04","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-generation","task_name":"3D Generation"},{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"point-cloud-generation","task_name":"Point Cloud Generation"},{"task_slug":"surface-reconstruction","task_name":"Surface Reconstruction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"hierarchical-vae","method_name":"Hierarchical VAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/point-cloud-generation-on-shapenet","task":"Point Cloud Generation","dataset":"ShapeNet","model":"LION","rank_in_archive_order":2,"of":2,"metrics":{"1-NNA-CD":"51.85","1-NNA-EMD":"48.95"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-generation-on-shapenet-airplane","task":"Point Cloud Generation","dataset":"ShapeNet Airplane","model":"LION","rank_in_archive_order":1,"of":5,"metrics":{"1-NNA-CD":"53.47","1-NNA-EMD":"53.84"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-generation-on-shapenet-car","task":"Point Cloud Generation","dataset":"ShapeNet Car","model":"LION","rank_in_archive_order":2,"of":5,"metrics":{"1-NNA-CD":"54.81","1-NNA-EMD":"50.53"},"uses_additional_data":false},{"leaderboard":"/sota/point-cloud-generation-on-shapenet-chair","task":"Point Cloud Generation","dataset":"ShapeNet Chair","model":"LION","rank_in_archive_order":2,"of":5,"metrics":{"1-NNA-CD":"52.07","1-NNA-EMD":"48.67"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.06978","atlas_url":"https://app.syntology.ai/?focus=2210.06978","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":"2210.06978"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2210.06978\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2210.06978"},"call":"get_concepts_for_paper(arxiv_id=\"2210.06978\")"}],"by_repo":[{"repo":"nv-tlabs/LION","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MS-Mind/MS-Code-04","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"d09235da68050ef3fe22cf78063dc4498a0f6e0e9fe2a83eaf43bc1fbc5488c3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}