Picture for Hanxin Zhu

Hanxin Zhu

TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generation

Add code
Dec 13, 2024
Viaarxiv icon

Compositional 3D-aware Video Generation with LLM Director

Add code
Aug 31, 2024
Viaarxiv icon

UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt

Add code
Jul 18, 2024
Viaarxiv icon

GaussianSR: 3D Gaussian Super-Resolution with 2D Diffusion Priors

Add code
Jun 14, 2024
Viaarxiv icon

Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?

Add code
Mar 10, 2024
Figure 1 for Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
Figure 2 for Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
Figure 3 for Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
Figure 4 for Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis?
Viaarxiv icon

SeD: Semantic-Aware Discriminator for Image Super-Resolution

Add code
Feb 29, 2024
Viaarxiv icon

CMC: Few-shot Novel View Synthesis via Cross-view Multiplane Consistency

Add code
Feb 26, 2024
Viaarxiv icon

MiNL: Micro-images based Neural Representation for Light Fields

Add code
Sep 17, 2022
Figure 1 for MiNL: Micro-images based Neural Representation for Light Fields
Figure 2 for MiNL: Micro-images based Neural Representation for Light Fields
Figure 3 for MiNL: Micro-images based Neural Representation for Light Fields
Figure 4 for MiNL: Micro-images based Neural Representation for Light Fields
Viaarxiv icon