Yangguang Li

papers

531

total citations

papers (11)

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

CVPR 2024arXiv

278

citations

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

CVPR 2024arXiv

citations

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

CVPR 2025arXiv

citations

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

ICCV 2025arXiv

citations

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

ECCV 2022arXiv

citations

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

NEURIPS 2025arXiv

citations

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation

AAAI 2024

citations

Yangguang Li

papers (11)

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

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

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

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

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

A Mixture Of Surprises for Unsupervised Reinforcement Learning

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

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

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

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

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation

papers (11)

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

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

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

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

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

A Mixture Of Surprises for Unsupervised Reinforcement Learning

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

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

Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies

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

Exploring Temporal Feature Correlation for Efficient and Stable Video Semantic Segmentation