Projects

Scaling Sequence-to-Sequence Generative Neural Rendering ^{[Paper] [Blog]}

Shikun Liu, Kam Woh Ng, Wonbong Jang, Jiadong Guo, Junlin Han, Haozhe Liu, Yiannis Douratsos, Juan C. Pérez, Zijian Zhou, Chi Phung, Tao Xiang, and Juan-Manuel Pérez-Rúa

MarDini: Masked Autoregressive Diffusion for Video Generation at Scale ^{[Paper] [Blog]}

Haozhe Liu, Shikun Liu, Zijian Zhou, Mengmeng Xu, Yanping Xie, Xiao Han, Juan C. Pérez, Ding Liu, Kumara Kahatapitiya, Menglin Jia, Jui-Chieh Wu, Sen He, Tao Xiang, Jürgen Schmidhuber, Juan-Manuel Pérez-Rúa

Learning Flow Fields in Attention for Controllable Person Image Generation ^{[Paper] [Demo] [Code]}

Zijian Zhou, Shikun Liu, Xiao Han, Haozhe Liu, Kam Woh Ng, Tian Xie, Yuren Cong, Hang Li, Mengmeng Xu, Juan-Manuel Pérez-Rúa, Aditya Patel, Tao Xiang, Miaojing Shi, Sen He

EscherNet: A Generative Model for Scalable View Synthesis ^{[Paper] [Blog] [Code]}

Xin Kong, Shikun Liu, Xiaoyang Lyu, Marwan Taher, Xiaojuan Qi, and Andrew J. Davison

Prismer: A Vision-Language Model with Multi-Task Experts ^{[Paper] [Blog] [Code] [Demo]}

Shikun Liu, Linxi Fan, Edward Johns, Zhiding Yu, Chaowei Xiao, and Anima Anandkumar

vMAP: Vectorised Object Mapping for Neural Field SLAM ^{[Paper] [Blog] [Code]}

Xin Kong, Shikun Liu, Marwan Taher, and Andrew J. Davison

Auto-Lambda: Disentangling Dynamic Task Relationships ^{[Paper] [Blog] [Code] [Slides]}

Shikun Liu, Stephen James, Andrew J. Davison, and Edward Johns

Bootstrapping Semantic Segmentation with Regional Contrast ^{[Paper] [Blog] [Code] [Slides]}

Shikun Liu, Shuaifeng Zhi, Edward Johns, and Andrew J. Davison

iMAP: Implicit Mapping and Positioning in Real-Time ^{[Paper] [Blog] [Code] [Video]}

Edgar Sucar, Shikun Liu, Joseph Ortiz, and Andrew J. Davison

Shape Adaptor: A Learnable Resizing Module ^{[Paper] [Blog] [Code] [Slides]}

Shikun Liu, Zhe Lin, Yilin Wang, Jianming Zhang, Federico Perazzi, and Edward Johns

Self-Supervised Generalisation with Meta Auxiliary Learning ^{[Paper] [Blog] [Code] [Slides]}

Shikun Liu, Andrew J. Davison, and Edward Johns

End-to-End Multi-Task Learning with Attention ^{[Paper] [Blog] [Code]}

Shikun Liu, Edward Johns, and Andrew J. Davison

Learning a Hierarchical Latent-Variable Model of 3D Shapes ^{[Paper] [Blog] [Code]}

Shikun Liu, C. Lee Giles, and Alexander G. Ororbia II.