3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents them as neural fields. The concept of neural fields has previously been combined with a global latent vector, a regular grid of latent vectors, or an irregular grid of latent vectors. Our new representation encodes neural fields on top of a set of vectors. We draw from multiple concepts, such as the radial basis function representation and the cross attention and self-attention function, to design a learnable representation that is especially suitable for processing with transformers. Our results show improved performance in 3D shape encoding and 3D shape generative modeling tasks. We demonstrate a wide variety of generative applications: unconditioned generation, category-conditioned generation, text-conditioned generation, point-cloud completion, and image-conditioned generation.
Code (2)
Tasks
3D Shape RepresentationPoint Cloud CompletionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Improving Handshape Representations for Sign Language Processing: A Graph Neural Network Approach
Handshapes serve a fundamental phonological role in signed languages, with American Sign Language employing approximately 50 distinct shapes. However,computational approaches rarely model handshapes explicitly, limiting …
Graph Neural NetworkContrastive LearningMotion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking
We introduce Motion2VecSets, a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. While existing state-of-the-art methods have demonstrated success in reconstructing non-rigid objects using…
4D reconstructionDenoisingObject TrackingSurface ReconstructionMemorization in 3D Shape Generation: An Empirical Study
Generative models are increasingly used in 3D vision to synthesize novel shapes, yet it remains unclear whether their generation relies on memorizing training shapes. Understanding their memorization could help prevent t…
AutoPartGen: Autogressive 3D Part Generation and Discovery
We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the object's parts, or an existing 3D object, and…
3D Generation3D ReconstructionObjectHigh-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering
Readily editable mesh blendshapes have been widely used in animation pipelines, while recent advancements in neural geometry and appearance representations have enabled high-quality inverse rendering. Building upon these…
Inverse Rendering