{"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/lidpm-rethinking-point-diffusion-for-lidar","title":"LiDPM: Rethinking Point Diffusion for Lidar Scene Completion","arxiv_id":"2504.17791","date":"2025-04-24","proceeding":null,"authors":["Tetiana Martyniuk","Gilles Puy","Alexandre Boulch","Renaud Marlet","Raoul de Charette"],"abstract":"Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM .","url_abs":"https://arxiv.org/abs/2504.17791v1","url_pdf":"https://arxiv.org/pdf/2504.17791v1.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":"lidpm-rethinking-point-diffusion-for-lidar","repo_url":"https://github.com/astra-vision/LiDPM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"lidar-scene-completion","task_name":"Lidar Scene Completion"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lidar-scene-completion-on-semantickitti","task":"Lidar Scene Completion","dataset":"SemanticKITTI","model":"LiDPM (refined)","rank_in_archive_order":2,"of":4,"metrics":{"Chamfer Distance":"0.377","JSD 3D":"0.542","JSD BEV":"0.403","Voxel IoU 0.1m":"14.93","Voxel IoU 0.2m":"25.76","Voxel IoU 0.5m":"36.59"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-scene-completion-on-semantickitti","task":"Lidar Scene Completion","dataset":"SemanticKITTI","model":"LiDPM","rank_in_archive_order":4,"of":4,"metrics":{"Chamfer Distance":"0.446","JSD 3D":"0.532","JSD BEV":"0.440","Voxel IoU 0.1m":"6.27","Voxel IoU 0.2m":"19.45","Voxel IoU 0.5m":"34.09"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2504.17791","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}