Get the latest tech news
GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation
-quality and editable surfel Gaussians through a cascaded 3D diffusion pipeline, given single-view images or texts as the conditions. While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations.
While 3D content generation has advanced significantly, existing methods still face challenges with input formats, latent space design, and output representations. We believe the proposed method has much potential and scales better with more data and compute resources, and yield better 3D editing performance due to its compatability with diffusion model. @article{lan2024ga, title={GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D 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}, eprint={2411.08033}, primaryClass={cs.CV}, year={2024} }
Or read this on Hacker News