Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation
원문 초록
This paper presents a new approach for 3D shape generation, inversion, and manipulation, through a direct generative modeling on a continuous implicit representation in wavelet domain. Specifically, we propose a compact wavelet representation with a pair of coarse and detail coefficient volumes to implicitly represent 3D shapes via truncated signed distance functions and multi-scale biorthogonal wavelets. Then, we design a pair of neural networks: a diffusion-based generator to produce diverse shapes in the form of the coarse coefficient volumes and a detail predictor to produce compatible detail coefficient volumes for introducing fine structures and details. Further, we may jointly train an encoder network to learn a latent space for inverting shapes, allowing us to enable a rich variety of whole-shape and region-aware shape manipulations. Both quantitative and qualitative experimental results manifest the compelling shape generation, inversion, and manipulation capabilities of our approach over the state-of-the-art methods.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation
Unleashing Vecset Diffusion Model for Fast Shape Generation
Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
OctFusion: Octree-based Diffusion Models for 3D Shape Generation
Score Distillation via Reparametrized DDIM
토론
이 논문과 연결된 포럼 글이 아직 없습니다.