{"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/generalized-deep-3d-shape-prior-via-part","title":"Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Yuhan Li","Yishun Dou","Xuanhong Chen","Bingbing Ni","Yilin Sun","Yutian Liu","Fuzhen Wang"],"abstract":"    We develop a generalized 3D shape generation prior model, tailored for multiple 3D tasks including unconditional shape generation, point cloud completion, and cross-modality shape generation, etc. On one hand, to precisely capture local fine detailed shape information, a vector quantized variational autoencoder (VQ-VAE) is utilized to index local geometry from a compactly learned codebook based on a broad set of task training data. On the other hand, a discrete diffusion generator is introduced to model the inherent structural dependencies among different tokens. In the meantime, a multi-frequency fusion module (MFM) is developed to suppress high-frequency shape feature fluctuations, guided by multi-frequency contextual information. The above designs jointly equip our proposed 3D shape prior model with high-fidelity, diverse features as well as the capability of cross-modality alignment, and extensive experiments have demonstrated superior performances on various 3D shape generation tasks.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Li_Generalized_Deep_3D_Shape_Prior_via_Part-Discretized_Diffusion_Process_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Li_Generalized_Deep_3D_Shape_Prior_via_Part-Discretized_Diffusion_Process_CVPR_2023_paper.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":"generalized-deep-3d-shape-prior-via-part","repo_url":"https://github.com/colorful-liyu/3dqd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-shape-generation","task_name":"3D Shape Generation"},{"task_slug":"point-cloud-completion","task_name":"Point Cloud Completion"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}