Picture for Shanxin Yuan

Shanxin Yuan

HandSplat: Embedding-Driven Gaussian Splatting for High-Fidelity Hand Rendering

Add code
Mar 18, 2025
Viaarxiv icon

SuperCap: Multi-resolution Superpixel-based Image Captioning

Add code
Mar 11, 2025
Viaarxiv icon

HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stage

Add code
Mar 03, 2025
Viaarxiv icon

ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization

Add code
Oct 28, 2024
Viaarxiv icon

Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss

Add code
Sep 13, 2024
Figure 1 for Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
Figure 2 for Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
Figure 3 for Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
Figure 4 for Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a Region-Aware Cycle Loss
Viaarxiv icon

Exploring Effective Mask Sampling Modeling for Neural Image Compression

Add code
Jun 09, 2023
Viaarxiv icon

NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds

Add code
Apr 13, 2023
Viaarxiv icon

Graph Neural Networks in Vision-Language Image Understanding: A Survey

Add code
Mar 07, 2023
Viaarxiv icon

Low-Light Video Enhancement with Synthetic Event Guidance

Add code
Aug 23, 2022
Figure 1 for Low-Light Video Enhancement with Synthetic Event Guidance
Figure 2 for Low-Light Video Enhancement with Synthetic Event Guidance
Figure 3 for Low-Light Video Enhancement with Synthetic Event Guidance
Figure 4 for Low-Light Video Enhancement with Synthetic Event Guidance
Viaarxiv icon

Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment

Add code
Aug 05, 2022
Figure 1 for Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment
Figure 2 for Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment
Figure 3 for Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment
Figure 4 for Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment
Viaarxiv icon