Picture for Ying Shan

Ying Shan

Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos

Add code
Oct 15, 2024
Viaarxiv icon

Editing Music with Melody and Text: Using ControlNet for Diffusion Transformer

Add code
Oct 07, 2024
Viaarxiv icon

E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding

Add code
Sep 26, 2024
Viaarxiv icon

StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos

Add code
Sep 11, 2024
Viaarxiv icon

Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Add code
Sep 06, 2024
Viaarxiv icon

ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

Add code
Sep 03, 2024
Viaarxiv icon

DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

Add code
Sep 03, 2024
Figure 1 for DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Figure 2 for DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Figure 3 for DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Figure 4 for DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos
Viaarxiv icon

CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities

Add code
Aug 23, 2024
Figure 1 for CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
Figure 2 for CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
Figure 3 for CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
Figure 4 for CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
Viaarxiv icon

Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models

Add code
Aug 21, 2024
Viaarxiv icon

SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses

Add code
Aug 07, 2024
Figure 1 for SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses
Figure 2 for SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses
Figure 3 for SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses
Figure 4 for SynopGround: A Large-Scale Dataset for Multi-Paragraph Video Grounding from TV Dramas and Synopses
Viaarxiv icon