SPA-VAE: Similar-Parts-Assignment for Unsupervised 3D Point Cloud Generation
원문 초록
This paper addresses the problem of unsupervised parts-aware point cloud generation with learned parts-based self-similarity. Our SPA-VAE infers a set of latent canonical candidate shapes for any given object, along with a set of rigid body transformations for each such candidate shape to one or more locations within the assembled object. In this way, noisy samples on the surface of, say, each leg of a table, are effectively combined to estimate a single leg prototype. When parts-based self-similarity exists in the raw data, sharing data among parts in this way confers numerous advantages: modeling accuracy, appropriately self-similar generative outputs, precise in-filling of occlusions, and model parsimony. SPA-VAE is trained end-to-end using a variational Bayesian approach which uses the Gumbel-softmax trick for the shared part assignments, along with various novel losses to provide appropriate inductive biases. Quantitative and qualitative analyses on ShapeNet demonstrate the advantage of SPA-VAE.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
TopoDiT-3D: Topology-Aware Diffusion Transformer with Bottleneck Structure for 3D Point Cloud Generation
EAGLE: Contextual Point Cloud Generation via Adaptive Continuous Normalizing Flow with Self-Attention
Generative diffusion model with inverse renormalization group flows
ObitoNet: Multimodal High-Resolution Point Cloud Reconstruction
PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.