Stephen James

Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

May 31, 2021
Stephen James, Andrew J. Davison

Figure 2 for Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

Figure 3 for Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

Figure 4 for Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation

* Videos and code found at: https://sites.google.com/view/q-attention

Access Paper or Ask Questions

Waypoint Planning Networks

May 01, 2021
Alexandru-Iosif Toma, Hussein Ali Jaafar, Hao-Ya Hsueh, Stephen James, Daniel Lenton, Ronald Clark, Sajad Saeedi

* The Conference on Robots and Vision (CRV2021) Supplementary Website: https://sites.google.com/view/waypoint-planning-networks

Access Paper or Ask Questions

SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks

Mar 30, 2021
Zoe Landgraf, Raluca Scona, Tristan Laidlow, Stephen James, Stefan Leutenegger, Andrew J. Davison

Figure 2 for SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks

Figure 3 for SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks

Figure 4 for SIMstack: A Generative Shape and Instance Model for Unordered Object Stacks

Access Paper or Ask Questions

End-to-End Egospheric Spatial Memory

Feb 17, 2021
Daniel Lenton, Stephen James, Ronald Clark, Andrew J. Davison

Figure 2 for End-to-End Egospheric Spatial Memory

Figure 3 for End-to-End Egospheric Spatial Memory

Figure 4 for End-to-End Egospheric Spatial Memory

* Conference paper at ICLR 2021. Implementation: https://github.com/ivy-dl/memory Project page: https://djl11.github.io/ESM/

Access Paper or Ask Questions