Yangguang Li

11

Papers

336

Total Citations

Papers (11)

Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers

GVGEN: Text-to-3D Generation with Volumetric Representation

PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation

A Mixture Of Surprises for Unsupervised Reinforcement Learning