5 papers
LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
Henry Howard-Jenkins, Jose-Raul Ruiz-Sarmiento, Victor Adrian Prisacariu
We present LaLaLoc to localise in environments without the need for prior visitation, and in a manner that is robust to large changes in scene appearance, such as a full rearrangem…
Correspondence Networks with Adaptive Neighbourhood Consensus
Shuda Li, Kai Han, Theo W. Costain +2
In this paper, we tackle the task of establishing dense visual correspondences between images containing objects of the same category. This is a challenging task due to large intra…
FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation
Zirui Wang, Shuda Li, Henry Howard-Jenkins +2
We present FlowNet3D++, a deep scene flow estimation network. Inspired by classical methods, FlowNet3D++ incorporates geometric constraints in the form of point-to-plane distance a…
GroSS: Group-Size Series Decomposition for Grouped Architecture Search
Henry Howard-Jenkins, Yiwen Li, Victor A. Prisacariu
We present a novel approach which is able to explore the configuration of grouped convolutions within neural networks. Group-size Series (GroSS) decomposition is a mathematical for…
Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts
Henry Howard-Jenkins, Shuda Li, Victor Prisacariu
We propose a method for room layout estimation that does not rely on the typical box approximation or Manhattan world assumption. Instead, we reformulate the geometry inference pro…