Picture for Wangmeng Zuo

Wangmeng Zuo

Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors

Add code
Jul 13, 2024
Viaarxiv icon

Multi-modal Crowd Counting via a Broker Modality

Add code
Jul 10, 2024
Viaarxiv icon

Evaluation of Text-to-Video Generation Models: A Dynamics Perspective

Add code
Jul 01, 2024
Figure 1 for Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Figure 2 for Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Figure 3 for Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Figure 4 for Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Viaarxiv icon

CPT: Consistent Proxy Tuning for Black-box Optimization

Add code
Jul 01, 2024
Figure 1 for CPT: Consistent Proxy Tuning for Black-box Optimization
Figure 2 for CPT: Consistent Proxy Tuning for Black-box Optimization
Figure 3 for CPT: Consistent Proxy Tuning for Black-box Optimization
Figure 4 for CPT: Consistent Proxy Tuning for Black-box Optimization
Viaarxiv icon

LayerMatch: Do Pseudo-labels Benefit All Layers?

Add code
Jun 20, 2024
Viaarxiv icon

Diffusion Models in Low-Level Vision: A Survey

Add code
Jun 17, 2024
Figure 1 for Diffusion Models in Low-Level Vision: A Survey
Figure 2 for Diffusion Models in Low-Level Vision: A Survey
Figure 3 for Diffusion Models in Low-Level Vision: A Survey
Figure 4 for Diffusion Models in Low-Level Vision: A Survey
Viaarxiv icon

GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection

Add code
Jun 11, 2024
Viaarxiv icon

DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians with Video Diffusion Priors

Add code
Jun 03, 2024
Viaarxiv icon

Two Optimizers Are Better Than One: LLM Catalyst for Enhancing Gradient-Based Optimization

Add code
May 31, 2024
Viaarxiv icon

Improved Generation of Adversarial Examples Against Safety-aligned LLMs

Add code
May 28, 2024
Viaarxiv icon