ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
Taming large-scale video diffusion models for high-fidelity novel view synthesis.
Wangbo Yu
Research Scientist
Tencent ARC Lab
I obtained my Ph.D. from the School of Computer Science at Peking University, advised by Prof. Li Yuan and Prof. Yonghong Tian. Previously, I received my B.Eng. from Xidian University in 2021. My research spans 3D vision and generative models, with a recent focus on video world models.
I am actively building world model systems that support real-time generation, flexible interaction, and long-term memory. I am looking for research interns with relevant experience—feel free to contact me if you are interested.
Research Works ( )
TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
International Conference on Computer Vision (ICCV, Oral), 2025
Generating high-fidelity novel views from casually captured monocular video, while also supporting exact pose control.
HiFi-123: Towards High-fidelity One Image to 3D Content Generation
European Conference on Computer Vision (ECCV), 2024
High-fidelity and multi-view consistent 3D content generation from a single image.
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
ACM International Conference on Multimedia (ACM MM), 2025
arXiv
/
Project
/
Video
/
Code
Generating panoramic videos and reconstructing immersive 360-degree 4D scenes from a single prompt or reference image.
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
arXiv preprint, 2025
A unified generative framework for image understanding, generation, manipulation, and perception using high-resolution semantic encoders.
NOFA++: Tuning-free NeRF-based One-shot Facial Avatar Reconstruction
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025
A tuning-free framework for reconstructing high-fidelity, animatable 3D facial avatars from a single image.
NOFA: NeRF-based One-shot Facial Avatar Reconstruction
SIGGRAPH, 2023
A one-shot framework that reconstructs a high-fidelity, animatable 3D facial avatar from a single source image.
An Efficient Transformer Based on Global and Local Self-Attention for Face Photo-Sketch Synthesis
IEEE Transactions on Image Processing (TIP), 2023
An efficient GL-Transformer that combines global and local self-attention for structured and realistic face photo-sketch synthesis.
2026
Breaking the Vicious Cycle: Coherent 3D Gaussian Splatting from Sparse and Motion-Blurred Views
C. Feng, Z. Xu, Y. Li, J. Zhao, J. Yang, W. Yu, L. Yuan, Y. Tian
IEEE Transactions on Circuits and Systems for Video Technology, 2026
DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images
C. Shi, W. Yu, C. Feng, L. Yuan
arXiv preprint arXiv:2606.01315, 2026
Style-GRPO: Semantic-Aware Preference Optimization for Image Style Transfer Guided by Reward Modeling
J. Zhao, C. Feng, M. Yu, Y. Li, Z. Tang, W. Yu, Y. Zhao, X. Li, L. Yuan, Y. Tian
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
360Explorer: Exploring 4D Controllable World in Panoramic Videos
X. Cheng, H. Zhou, W. Yu, T. Jia, B. Lin, Y. Ge, W. Li, L. Yuan
AAAI Conference on Artificial Intelligence (AAAI), 2026
EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View Synthesis
W. Yu, C. Feng, J. Li, A. Zhang, Z. Tang, M. Guo, W. Zhang, Z. Ma, L. Yuan, et al.
International Conference on Learning Representations (ICLR), 2026
2025
NOFA++: Tuning-free NeRF-based One-shot Facial Avatar Reconstruction
W. Yu, C. Feng, L. Yuan, Y. Tian
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2025
UniWorld-V2: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback
Z. Li, Z. Liu, Q. Zhang, B. Lin, F. Wu, S. Yuan, Z. Yan, Y. Ye, W. Yu, et al.
arXiv preprint arXiv:2510.16888, 2025
E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras
C. Feng*, Z. Tang*, W. Yu*, Y. Pang, Y. Zhao, J. Zhao, L. Yuan, Y. Tian
ACM International Conference on Multimedia (ACM MM), 2025
UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
B. Lin, Z. Li, X. Cheng, Y. Niu, Y. Ye, X. He, S. Yuan, W. Yu, et al.
arXiv preprint arXiv:2506.03147, 2025
GS2E: Gaussian Splatting Is an Effective Data Generator for Event Stream Generation
Y. Li, C. Feng, Z. Tang, K. Deng, W. Yu, Y. Tian, L. Yuan
Advances in Neural Information Processing Systems (NeurIPS), 2025
HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation
H. Zhou*, W. Yu*, J. Guan, X. Cheng, Y. Tian, L. Yuan
ACM International Conference on Multimedia (ACM MM), 2025
NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations
Z. Tang, C. Feng, X. Cheng, W. Yu, J. Zhang, Y. Liu, X. Long, W. Wang, L. Yuan
AAAI Conference on Artificial Intelligence (AAAI), 2025
Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models
M. Cao, P. Hu, Y. Wang, J. Gu, H. Tang, H. Zhao, C. Wang, J. Dong, W. Yu, et al.
AAAI Conference on Artificial Intelligence (AAAI), 2025
AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scene
C. Feng, W. Yu, X. Cheng, Z. Tang, J. Zhang, L. Yuan, Y. Tian
AAAI Conference on Artificial Intelligence (AAAI), 2025
TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
M. Yu, W. Hu, J. Xing, Y. Shan
IEEE International Conference on Computer Vision (ICCV), Oral, 2025
2024
RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing
Z. Huang, W. Yu, X. Cheng, C.-S. Zhao, Y. Ge, M. Guo, L. Yuan, Y. Tian
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024
ViewCrafter: Taming Video Diffusion Models for High-Fidelity Novel View Synthesis
W. Yu, J. Xing, L. Yuan, W. Hu, X. Li, Z. Huang, X. Gao, T.-T. Wong, Y. Shan, et al.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024
Cycle3D: High-Quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
Z. Tang, J. Zhang, X. Cheng, W. Yu, C. Feng, Y. Pang, B. Lin, L. Yuan
AAAI Conference on Artificial Intelligence (AAAI), 2024
HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions
H. Zhou, X. Cheng, W. Yu, Y. Tian, L. Yuan
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2024
Multi-Scale Image Stitching Based on Unsupervised Controllable Fusion Structure
Y. Li, W. Yu, Y. Zhu, G. Luo
IEEE International Joint Conference on Neural Networks (IJCNN), 2024
EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
W. Yu, C. Feng, J. Tang, J. Yang, Z. Tang, X. Jia, Y. Yang, L. Yuan, Y. Tian
IEEE International Conference on Computer Vision (ICCV), 2024
AdaIFL: Adaptive Image Forgery Localization via a Dynamic and Importance-Aware Transformer Network
Y. Li, F. Cheng, W. Yu, G. Wang, G. Luo, Y. Zhu
European Conference on Computer Vision (ECCV), 2024
2023
DynamiCrafter: Animating Open-Domain Images with Video Diffusion Priors
J. Xing, M. Xia, Y. Zhang, H. Chen, W. Yu, X. Wang, T.-T. Wong, Y. Shan
European Conference on Computer Vision (ECCV), Oral, 2023
HiFi-123: Towards High-Fidelity One Image to 3D Content Generation
W. Yu, L. Yuan, Y.-P. Cao, X. Gao, X. Li, L. Quan, Y. Shan, Y. Tian
European Conference on Computer Vision (ECCV), 2023
NOFA: NeRF-Based One-Shot Facial Avatar Reconstruction
W. Yu, Y. Fan, Y. Zhang, X. Wang, F. Yin, Y. Bai, Y.-P. Cao, Y. Shan, Y. Wu, et al.
ACM SIGGRAPH, 2023
2022
An Efficient Transformer Based on Global and Local Self-Attention for Face Photo-Sketch Synthesis
W. Yu, M. Zhu, N. Wang, X. Wang, X. Gao
IEEE Transactions on Image Processing (TIP), 2022
Interactive Image Inpainting Using Semantic Guidance
W. Yu, J. Du, R. Liu, Y. Li, Y. Zhu
IEEE International Conference on Pattern Recognition (ICPR), 2022
Awards
- Excellent Graduate of Peking University, 2026
- Excellent Graduate of Shaanxi Province, 2021
- National Scholarship of China, 2020
- National Scholarship of China, 2019
Workshop
- Area Chair: 2nd HiGen @CVPR 2026.
- Area Chair: 1st HiGen @ICCV 2025.
Academic Services
- Journal Review: IEEE Transactions on Visualization and Computer Graphics (TVCG) International Journal of Computer Vision (IJCV) IEEE Transactions on Multimedia (TMM) IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
- Conference Review: SIGGRAPH, CVPR, ICCV, ECCV, ICLR, NeurIPS, ACM MM