Zhaoxi Chen

15

Papers

664

Total Citations

Papers (15)

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

Generative Gaussian Splatting for Unbounded 3D City Generation

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

NeurIPS 2025arXiv

Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers

CityDreamer: Compositional Generative Model of Unbounded 3D Cities

F2-NeRF: Fast Neural Radiance Field Training With Free Camera Trajectories

Adaptive Focus for Efficient Video Recognition

SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling

SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis

Relighting4D: Neural Relightable Human from Videos

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

Dual-Expert Consistency Model for Efficient and High-Quality Video Generation

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency

URHand: Universal Relightable Hands

PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation