Picture for Hanyang Wang

Hanyang Wang

VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step

Add code
Apr 03, 2025
Viaarxiv icon

Video-T1: Test-Time Scaling for Video Generation

Add code
Mar 24, 2025
Viaarxiv icon

Robust Dynamic Facial Expression Recognition

Add code
Feb 22, 2025
Viaarxiv icon

Bayesian Optimization with Preference Exploration by Monotonic Neural Network Ensemble

Add code
Jan 30, 2025
Viaarxiv icon

Respecting the limit:Bayesian optimization with a bound on the optimal value

Add code
Nov 07, 2024
Figure 1 for Respecting the limit:Bayesian optimization with a bound on the optimal value
Figure 2 for Respecting the limit:Bayesian optimization with a bound on the optimal value
Figure 3 for Respecting the limit:Bayesian optimization with a bound on the optimal value
Figure 4 for Respecting the limit:Bayesian optimization with a bound on the optimal value
Viaarxiv icon

Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint

Add code
Aug 31, 2024
Figure 1 for Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
Figure 2 for Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
Figure 3 for Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
Figure 4 for Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
Viaarxiv icon

ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

Add code
Aug 29, 2024
Viaarxiv icon

Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion

Add code
Jun 07, 2024
Viaarxiv icon

Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

Add code
May 30, 2024
Figure 1 for Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Figure 2 for Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Figure 3 for Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Figure 4 for Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Viaarxiv icon

Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition

Add code
Mar 28, 2024
Viaarxiv icon