← Authors

Fangzhou Hong

24 papers · 2021–2025 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (5) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (39) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (20) πŸ‘₯ Mega-Team (22) ⚑ Prolific Year (7) πŸ’Ž Century Club (24) πŸ”₯ Unstoppable (5) πŸ—ƒοΈ Keyword Collector (102)

Conferences

CVPR (10) ECCV (5) ICCV (3) ICLR (3) NIPS (3)

Top co-authors

Ziwei Liu (20) Liang Pan (8) Zhongang Cai (6) Lei Yang (6) Chen Change Loy (5) Zhaoxi Chen (5) Yushi Lan (5) Shuai Yang (4) Mingyuan Zhang (3) Haozhe Xie (3)

Keywords

neural radiance field (4) diffusion model (3) generative model (3) point cloud (3) autonomous driving (3) novel view synthesis (3) 3d reconstruction (3) 3d generation (3) 3d city generation (2) semantic segmentation (2) large language model (2) egocentric video (2) retrieval-augmented generation (2) panoptic segmentation (2) scene representation (2) motion generation (2) volumetric rendering (2) 3d vision (1) temporal modeling (1) multimodal learning (1)

Papers

GaussianAnything: Interactive Point Cloud Flow Matching for 3D Generation ICLR 2025
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion CVPR 2025
EgoLife: Towards Egocentric Life Assistant CVPR 2025
EgoLM: Multi-Modal Language Model of Egocentric Motions CVPR 2025
Generative Gaussian Splatting for Unbounded 3D City Generation CVPR 2025
MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention CVPR 2025
CityDreamer: Compositional Generative Model of Unbounded 3D Cities CVPR 2024
SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering CVPR 2024
Large-Vocabulary 3D Diffusion Model with Transformer ICLR 2024
LN3Diff: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation ECCV 2024
Large Motion Model for Unified Multi-Modal Motion Generation ECCV 2024
Nymeria: A Massive Collection of Egocentric Multi-modal Human Motion in the Wild ECCV 2024
StructLDM: Structured Latent Diffusion for 3D Human Generation ECCV 2024
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model ICCV 2023
SHERF: Generalizable Human NeRF from a Single Image ICCV 2023
PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation NIPS 2023
EVA3D: Compositional 3D Human Generation from 2D Image Collections ICLR 2023
4D Panoptic Scene Graph Generation NIPS 2023
DeformToon3D: Deformable Neural Radiance Fields for 3D Toonification ICCV 2023
HuMMan: Multi-modal 4D Human Dataset for Versatile Sensing and Modeling ECCV 2022
Versatile Multi-Modal Pre-Training for Human-Centric Perception CVPR 2022
LiDAR-Based Panoptic Segmentation via Dynamic Shifting Network CVPR 2021
Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation CVPR 2021
Garment4D: Garment Reconstruction from Point Cloud Sequences NIPS 2021