activity
20182022
most citedTowards General and Autonomous Learning of Core Skills: A Case Study in Locomotion

10 citations · 30 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

5 papers · 1 filter

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.CV20199 cited

SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations

Shuaifeng Zhi, Michael Bloesch, Stefan Leutenegger +1

Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been…

cs.CV2018

LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo

Ronald Clark, Michael Bloesch, Jan Czarnowski +2

Sum-of-squares objective functions are very popular in computer vision algorithms. However, these objective functions are not always easy to optimize. The underlying assumptions ma…

cs.CV2018

Fusion++: Volumetric Object-Level SLAM

John McCormac, Ronald Clark, Michael Bloesch +2

We propose an online object-level SLAM system which builds a persistent and accurate 3D graph map of arbitrary reconstructed objects. As an RGB-D camera browses a cluttered indoor…

cs.CV2018

CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM

Michael Bloesch, Jan Czarnowski, Ronald Clark +2

The representation of geometry in real-time 3D perception systems continues to be a critical research issue. Dense maps capture complete surface shape and can be augmented with sem…