Xiaoyu Li

发表论文 21 篇 · 总被引 1081 次 · h-index 14

代表论文

• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis (2024 · IEEE Transactions on Pattern Analysis and Machine Intelligence · 被引 394)
• DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos (2024 · Computer Vision and Pattern Recognition · 被引 229)
• Advances in 3D Generation: A Survey (2024 · arXiv.org · 被引 94)
• DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation (2024 · Computer Vision and Pattern Recognition · 被引 80)
• CV-VAE: A Compatible Video VAE for Latent Generative Video Models (2024 · Neural Information Processing Systems · 被引 77)
• Geometrycrafter: Consistent Geometry Estimation for Open-World Videos With Diffusion Priors (2025 · IEEE International Conference on Computer Vision · 被引 41)