Sign up to save your podcasts
Or
Share Learning 3D Representations from Procedural 3D Programs
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Learning 3D Representations from Procedural 3D Programs
🤗 Paper Upvotes: 8 | cs.CV
Authors:
Xuweiyi Chen, Zezhou Cheng
Title:
Learning 3D Representations from Procedural 3D Programs
Arxiv:
http://arxiv.org/abs/2411.17467v1
Abstract:
Self-supervised learning has emerged as a promising approach for acquiring transferable 3D representations from unlabeled 3D point clouds. Unlike 2D images, which are widely accessible, acquiring 3D assets requires specialized expertise or professional 3D scanning equipment, making it difficult to scale and raising copyright concerns. To address these challenges, we propose learning 3D representations from procedural 3D programs that automatically generate 3D shapes using simple primitives and augmentations. Remarkably, despite lacking semantic content, the 3D representations learned from this synthesized dataset perform on par with state-of-the-art representations learned from semantically recognizable 3D models (e.g., airplanes) across various downstream 3D tasks, including shape classification, part segmentation, and masked point cloud completion. Our analysis further suggests that current self-supervised learning methods primarily capture geometric structures rather than high-level semantics.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Paper Upvotes: 8 | cs.CV
Authors:
Xuweiyi Chen, Zezhou Cheng
Title:
Learning 3D Representations from Procedural 3D Programs
Arxiv:
http://arxiv.org/abs/2411.17467v1
Abstract:
Self-supervised learning has emerged as a promising approach for acquiring transferable 3D representations from unlabeled 3D point clouds. Unlike 2D images, which are widely accessible, acquiring 3D assets requires specialized expertise or professional 3D scanning equipment, making it difficult to scale and raising copyright concerns. To address these challenges, we propose learning 3D representations from procedural 3D programs that automatically generate 3D shapes using simple primitives and augmentations. Remarkably, despite lacking semantic content, the 3D representations learned from this synthesized dataset perform on par with state-of-the-art representations learned from semantically recognizable 3D models (e.g., airplanes) across various downstream 3D tasks, including shape classification, part segmentation, and masked point cloud completion. Our analysis further suggests that current self-supervised learning methods primarily capture geometric structures rather than high-level semantics.