Authors: Yushi Lan, Shangchen Zhou, Zhaoyang Lyu, Fangzhou Hong, Shuai Yang, Bo Dai, Xingang Pan, Chen Change Loy
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.
Source: http://arxiv.org/abs/2411.08033v1
