25 Jun 2026
Oxford Visual Geometry Group researchers awarded Best Paper at CVPR 2026
The novel AI method reconstructs dynamic 3D scenes from video in seconds
The photo shows some of the authors at the conference award ceremony. Chuhan Zhang is receiving the award with Junyu Xie standing to her left.
A team of Oxford Engineering and Google DeepMind researchers has received the prestigious Best Paper Award at CVPR 2026 for their work Efficiently Reconstructing Dynamic Scenes One D4RT at a Time. This award recognises the top publication out of more than 16,000 submissions to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) - the principal international conference on computer vision.
The paper was authored by researchers who are current or former members of the Oxford Visual Geometry Group (VGG), together with researchers at Google DeepMind. The VGG researchers are Chuhan Zhang, Liliane Momeni, and Junyu Xie (a current DPhil student), together with Andrew Zisserman (a Royal Society Professor in Engineering Science).
The winning paper introduces D4RT, a novel approach for 3D reconstruction from a video of a dynamic scene using deep neural networks. It can predict a scene’s full 3D geometry, including the cameras, scene depth, and correspondences across the video frames. Unlike previous approaches, D4RT can make predictions for dynamic scenes with moving objects, as well as static scenes. It can carry out these multiple tasks from a video in just a few seconds.
This is the third time that the Visual Geometry Group has won the Best Paper Award at CVPR over the last six years. The VGG also received the award in 2020 and 2025 for the papers:
● VGGT: Visual Geometry Grounded Transformer, by Jianyuan Wang, Minghao Chen, Nikita Karaev, Andrea Vedaldi, Christian Rupprecht and David Novotny, CVPR 2025
● Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild, by Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi, CVPR 2020
After three decades, the VGG is still one of the most impactful computer vision groups worldwide.
Professor Andrew Zisserman says: “This is an excellent team effort. It shows the power of combining good ideas – in this case, a simpler model for these tasks than prior work – with wonderful compute resources, and an incredible team to enable the investigation.”
