3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models

By Biao Zhang, Jiapeng Tang, Matthias Nießner, Peter Wonka. ACM Transactions on Graphics, 2023

520 citations recorded by the source corpus.

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: https://1zb.github.io/3DShape2VecSet/.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/eb35863662544c977780299c21e669555ae83e81

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Minghua Liu
2. Ziwei Liu
3. Yuanchen Guo
4. Chao Xu
5. Taku Komura
6. Lingjie Liu
7. Hao Su
8. Jiaxiang Tang

In Computer Graphics and Computer-Aided Design

1. Hao Su
2. Minghua Liu
3. Weihao Cheng
4. Ying Shan
5. Jiaxiang Tang
6. Gang Zeng
7. Jiawei Ren
8. Wenping Wang

In Computer Vision and Pattern Recognition

1. Ying Shan
2. Ziwei Liu
3. Chen Change Loy
4. Luc Van Gool
5. Xintao Wang
6. Yu Qiao
7. Ming-Hsuan Yang
8. Andreas Geiger

Citations in the corpus

• One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion (2023, background): “…directly from 3D synthetic data or real scans and generate various 3D representations such as point clouds [1, 15, 41, 47, 83], 3D voxels [9, 59, 74, 75], polygon meshes [16, 17, 26, 32, 37, 46, 68], parametric models [21], and implicit fields [8, 14, 19, 25, 30, 42, 48, 73, 78, 82, 84, 86, 87].”
• Structured 3D Latents for Scalable and Versatile 3D Generation (2024, unknown): “More Implementation Details”
• CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets (2024, methodology): “Specifically, we adopt the neural field design from 3DShape2VecSet [Zhang et al. 2023c] to depict continuous and complete surfaces along with a tailored multi-resolution geometry Variational Autoencoder (VAE).”
• InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models (2024, background): “With the rise of diffusion models, pioneer works have investigated image-conditioned 3D generative modeling on various representations, e.g ., point clouds [28, 32, 47, 55, 62], meshes [1, 25], SDF grids [6, 7, 44, 60] and neural fields [11, 16, 27, 31, 59].”
• Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation (2025, unknown): “To achieve this, we leverage 3DShape2VecSet [112] Michelangelo [119] Direct3D [99] advanced T2I models and corresponding conditional generation modules, such as ControlNet [115] and IP-Adapter [108], to generate input images that align with geometric shapes based on user-provided text or image…”
• Wonder3D: Single Image to 3D Using Cross-Domain Diffusion (2023, background): “There exists another group of works that endeavor to directly produce 3D geometries like point clouds [41, 45, 75, 80], meshes [16, 37], neural fields [1, 4, 8, 15, 17, 21, 26– 28, 44, 46, 65, 76] via network inference to avoid time-consuming per-shape optimization.”
• SyncDreamer: Generating Multiview-consistent Images from a Single-view Image (2023, background): “Many recent works [1, 7, 10, 17, 23, 27, 30, 31, 32, 34, 42, 45, 46, 48, 75, 87, 88] try to repeat the success of diffusion models on the 3D generation task.”
• DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation (2023, background): “…diffusion models usually work on a single object category and suffer from limited diversity (Jun & Nichol, 2023; Nichol et al., 2022; Gupta et al., 2023; Lorraine et al., 2023; Zhang et al., 2023; Zheng et al., 2023; Ntavelis et al., 2023; Chen et al., 2023b; Cheng et al., 2023; Gao et al., 2022).”