Chaoyang Wang

23

Papers

164

Total Citations

Papers (23)

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion

Explore In-Context Segmentation via Latent Diffusion Models

GTR: Improving Large 3D Reconstruction Models through Geometry and Texture Refinement

Lightweight Predictive 3D Gaussian Splats

Conditional Panoramic Image Generation via Masked Autoregressive Modeling

Learning Depth From Monocular Videos Using Direct Methods

PAUL: Procrustean Autoencoder for Unsupervised Lifting

Neural Prior for Trajectory Estimation

Reconstructing Animatable Categories From Videos

Flow Supervision for Deformable NeRF

Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction From a Single Image

Distill Knowledge From NRSfM for Weakly Supervised 3D Pose Learning

Object Proposal by Multi-Branch Hierarchical Segmentation

PrEditor3D: Fast and Precise 3D Shape Editing

T2Bs: Text-to-Character Blendshapes via Video Generation

OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography

LGMRec: Local and Global Graph Learning for Multimodal Recommendation

Towards Text-guided 3D Scene Composition

SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images

MBW: Multi-view Bootstrapping in the Wild

LightSpeed: Light and Fast Neural Light Fields on Mobile Devices

Autodecoding Latent 3D Diffusion Models