Paper · arXiv 2411.08033
GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation
Yushi Lan, Shangchen Zhou, Zhaoyang Lyu, Fangzhou Hong, Shuai Yang, Bo Dai, Xingang Pan, Chen Change Loy
A novel 3D generation framework using a VAE and cascaded latent diffusion model in a Point Cloud-structured Latent space achieves high-quality 3D generation with multi-modal inputs and disentangled shape-texture editing.
Abstract
While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. This paper introduces a novel 3D generation framework that addresses these challenges, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space. Our framework employs a Variational Autoencoder (VAE) with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information, and incorporates a cascaded latent diffusion model for improved shape-texture disentanglement. The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single/multi-view image inputs. Notably, the newly proposed latent space naturally enables geometry-texture disentanglement, thus allowing 3D-aware editing. Experimental results demonstrate the effectiveness of our approach on multiple datasets, outperforming existing methods in both text- and image-conditioned 3D generation.