Fangzhou Hong

9

Papers

122

Total Citations

Papers (9)

LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation

Generative Gaussian Splatting for Unbounded 3D City Generation

EgoLM: Multi-Modal Language Model of Egocentric Motions

GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data

3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion

CityDreamer: Compositional Generative Model of Unbounded 3D Cities

EgoLife: Towards Egocentric Life Assistant

MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering