Wei Cao

My research focuses on spatial intelligence for dynamic visual worlds, building models that reconstruct, generate, and reason about 3D/4D worlds from visual data for applications in video generation, embodied AI, and autonomous driving.

• Best Paper Award, CVPR 2026 Workshop on Generative Models for Computer Vision
• Oral Presentation, CVPR 2026 4D Vision Workshop: Modeling the Dynamic World
• Spotlight Talk, Midwest Machine Learning Symposium 2026

Google Scholar page

Cao, W., Zhang, H., Tian, F., Wu, Y., Li, Y., Wang, S., Yu, N., & Liu, Y. (2026). FreeOrbit4D: Training-free arbitrary camera redirection for monocular videos via foreground-complete 4D reconstruction. In ACM SIGGRAPH Conference Papers.

Tang, J., Cao, W., Zhang, B., Luo, C., Liu, Y., & Nießner, M. (2026). Motion2VecSets: Non-rigid shape reconstruction and tracking with 4D latent set diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Cao, W., Hallgarten, M., Li, T., Dauner, D., Gu, X., Wang, C., Miron, Y., Aiello, M., Li, H., Gilitschenski, I., Ivanovic, B., Pavone, M., Geiger, A., & Chitta, K. (2025). Pseudo-simulation for autonomous driving. In Conference on Robot Learning.

Zhou, H., Schmid, S., Li, Y., Halilaj, L., Yao, X., & Cao, W. (2025). Predicting the road ahead: A knowledge graph based foundation model for scene understanding in autonomous driving. In European Semantic Web Conference.

Cao, W., Luo, C., Zhang, B., Nießner, M., & Tang, J. (2024). Motion2VecSets: 4D latent vector set diffusion for non-rigid shape reconstruction and tracking. In IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Zhou, H., Cao, W., Sui, A., & Bing, Z. (2024). What matters to enhance traffic rule compliance of imitation learning for automated driving. In European Conference on Computer Vision Workshops.