activity
20152022
most citedSceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth

91 citations · 107 across the 6 of their papers we have counts for

collaborators
Showing cs.CVShow all

17 papers · 1 filter

cs.CV2021

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

Zoe Landgraf, Raluca Scona, Tristan Laidlow +3

By estimating 3D shape and instances from a single view, we can capture information about an environment quickly, without the need for comprehensive scanning and multi-view fusion.…

cs.CV2021

In-Place Scene Labelling and Understanding with Implicit Scene Representation

Shuaifeng Zhi, Tristan Laidlow, Stefan Leutenegger +1

Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes.…

cs.CV2020

Deep Probabilistic Feature-metric Tracking

Binbin Xu, Andrew J. Davison, Stefan Leutenegger

Dense image alignment from RGB-D images remains a critical issue for real-world applications, especially under challenging lighting conditions and in a wide baseline setting. In th…

cs.CV2020

Bundle Adjustment on a Graph Processor

Joseph Ortiz, Mark Pupilli, Stefan Leutenegger +1

Graph processors such as Graphcore's Intelligence Processing Unit (IPU) are part of the major new wave of novel computer architecture for AI, and have a general design with massive…

cs.CV2020

Comparing View-Based and Map-Based Semantic Labelling in Real-Time SLAM

Zoe Landgraf, Fabian Falck, Michael Bloesch +2

Generally capable Spatial AI systems must build persistent scene representations where geometric models are combined with meaningful semantic labels. The many approaches to labelli…

cs.CV2020

Towards Bounding-Box Free Panoptic Segmentation

Ujwal Bonde, Pablo F. Alcantarilla, Stefan Leutenegger

In this work we introduce a new Bounding-Box Free Network (BBFNet) for panoptic segmentation. Panoptic segmentation is an ideal problem for proposal-free methods as it already requ…