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 flow-based model for improved shape-texture disentanglement. The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single 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 native 3D methods in both text- and image-conditioned 3D generation.
@article{arxiv.2411.08033,
title = {GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation},
author = {Yushi Lan and Shangchen Zhou and Zhaoyang Lyu and Fangzhou Hong and Shuai Yang and Bo Dai and Xingang Pan and Chen Change Loy},
journal= {arXiv preprint arXiv:2411.08033},
year = {2025}
}