no code implementations • ICCV 2023 • Avishkar Saha, Oscar Mendez, Chris Russell, Richard Bowden
Our module can be readily integrated into existing pipelines involving graph convolution operations, replacing the predetermined or existing adjacency matrix with one that is learned, and optimized, as part of the general objective.
no code implementations • CVPR 2022 • Avishkar Saha, Oscar Mendez, Chris Russell, Richard Bowden
Estimating a semantically segmented bird's-eye-view (BEV) map from a single image has become a popular technique for autonomous control and navigation.
1 code implementation • 3 Oct 2021 • Avishkar Saha, Oscar Mendez Maldonado, Chris Russell, Richard Bowden
We show how a novel form of transformer network can be used to map from images and video directly to an overhead map or bird's-eye-view (BEV) of the world, in a single end-to-end network.