Picture for Xiaoyu Shi

Xiaoyu Shi

GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking

Add code
Jan 05, 2025
Viaarxiv icon

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Add code
Dec 10, 2024
Viaarxiv icon

BlinkVision: A Benchmark for Optical Flow, Scene Flow and Point Tracking Estimation using RGB Frames and Events

Add code
Oct 27, 2024
Viaarxiv icon

Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation

Add code
Mar 20, 2024
Figure 1 for Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
Figure 2 for Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
Figure 3 for Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
Figure 4 for Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
Viaarxiv icon

AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning

Add code
Feb 01, 2024
Figure 1 for AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
Figure 2 for AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
Figure 3 for AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
Figure 4 for AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
Viaarxiv icon

Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling

Add code
Jan 31, 2024
Figure 1 for Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
Figure 2 for Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
Figure 3 for Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
Figure 4 for Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
Viaarxiv icon

Cross-modality Attention Adapter: A Glioma Segmentation Fine-tuning Method for SAM Using Multimodal Brain MR Images

Add code
Jul 03, 2023
Viaarxiv icon

FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow

Add code
Jun 08, 2023
Viaarxiv icon

Context-TAP: Tracking Any Point Demands Spatial Context Features

Add code
Jun 03, 2023
Viaarxiv icon

A Unified Conditional Framework for Diffusion-based Image Restoration

Add code
May 31, 2023
Viaarxiv icon