Bio
Anyi Rao is a Postdoctoral Scholar at Stanford with Maneesh Agrawala. He has research experiences at Meta Reality Lab, Vector Institute, University of Toronto, Hong Kong University. He received the Ph.D. at MMLab in the Chinese University of Hong Kong in 2022, advised by Dahua Lin and Bolei Zhou. He studies human-centered AI for creativity, multimodality and film, with focuses on content generation, intelligent media editing and creation, semantic and cinematic analysis, aiming to build connections between AI and humans for collaborative intelligence and unleash human creativity and productivity. His works include ControlNet, AnimateDiff, MovieNet, Virtual Dynamic Storyboard, Shoot360, and CityNeRF.
Honors & Awards
-
Marr Prize (Best Paper Award), ICCV (2023)
-
Magic Grant, Brown Institue (2023)
-
Research Funding by Prime Video, Amazon (2023)
-
Grant for Organizing ICCV23 Creative Video Editing and Understanding Workshop, Pika, KAUST (2023)
-
Grant for Organizing ECCV22 Creative Video Editing and Understanding Workshop, KAUST (2022)
-
Grant for Organizing ICCV21 Creative Video Editing and Understanding Workshop, Adobe (2021)
-
Most Influential Papers, Paper Digest (2021)
Boards, Advisory Committees, Professional Organizations
-
Program Committee Member and Reviewer, CVPR, ICCV, ECCV, ACCV, SIGGRAPH, SIGGRAPH Asia, CHI, UIST, MM, NeurIPS, ICML, ICLR, AAAI, IJCAI (2021 - Present)
-
Leading/Key Organizer, CVPR2024/ICCV2023/ECCV2022/ICCV2021 Workshop AI for Creative Video Editing and Understanding (2021 - Present)
-
Founder, Virtual Film Studio https://virtualfilmstudio.github.io/ (2023 - Present)
-
Co-Founder, City-Super https://city-super.github.io/ (2021 - Present)
-
Co-Founder, MovieNet https://movienet.github.io/ (2020 - Present)
-
Journal Reviewer, IEEE Transactions on Multimedia, IEEE Transactions on Visualization and Computer Graphics, IEEE Transactions on Circuits and Systems for Video Technology, International Journal of Computer Vision (2021 - Present)
Current Research and Scholarly Interests
Human AI for Creativity, Computer Vision, Graphics, Human-Computer Interaction
All Publications
-
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
International Conference on Learning Representations
2024
View details for DOI 10.48550/arXiv.2307.04725
-
Adding Conditional Control to Text-to-Image Diffusion Models
IEEE/CVF International Conference on Computer Vision (ICCV)
2023
View details for DOI 10.1109/ICCV51070.2023.00355
-
Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production
SIGGRAPH Special Interest Group on Computer Graphics and Interactive Techniques Conference Poster
2023
View details for DOI 10.1145/3588028.3603647
-
Shoot360: Normal View Video Creation from City Panorama Footage
SIGGRAPH Special Interest Group on Computer Graphics and Interactive Techniques Conference
2022
View details for DOI 10.1145/3528233.3530702
-
BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
European Conference on Computer Vision (ECCV)
2022
View details for DOI 10.1007/978-3-031-19824-3_7
-
MovieNet: A Holistic Dataset for Movie Understanding
European Conference on Computer Vision (ECCV)
2020
View details for DOI 10.1007/978-3-030-58548-8_41
-
HotFlip: White-Box Adversarial Examples for Text Classification
Annual Meeting of the Association for Computational Linguistics (ACL)
2018
View details for DOI 10.18653/v1/p18-2006
- HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE International Joint Conference on Artificial Intelligence (IJCAI) 2023
-
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
The AAAI Conference on Artificial Intelligence
2023
View details for DOI 10.1609/aaai.v37i3.25495
-
A Coarse-to-Fine Framework for Automatic Video Unscreen
IEEE Transactions on Multimedia (TMM)
2022
View details for DOI 10.1109/TMM.2022.3150177
-
AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2022
View details for DOI 10.1109/CVPR52688.2022.01133
-
BlockPlanner: City Block Generation with Vectorized Graph Representation
IEEE/CVF International Conference on Computer Vision (ICCV)
2021
View details for DOI 10.1109/ICCV48922.2021.00503
-
Jointly Learning the Attributes and Composition of Shots for Boundary Detection in Videos
IEEE Transactions on Multimedia (TMM)
2021
View details for DOI 10.1109/tmm.2021.3092143
-
A Local-to-Global Approach to Multi-Modal Movie Scene Segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2020
View details for DOI 10.1109/cvpr42600.2020.01016
-
A Unified Framework for Shot Type Classification Based on Subject Centric Lens
European Conference on Computer Vision (ECCV)
2020
View details for DOI 10.1007/978-3-030-58621-8_2
-
Online Multi-modal Person Search in Videos
European Conference on Computer Vision (ECCV)
2020
View details for DOI 10.1007/978-3-030-58610-2_11