160 citations · 183 across the 5 of their papers we have counts for
7 papers
Towards the Probabilistic Fusion of Learned Priors into Standard Pipelines for 3D Reconstruction
Tristan Laidlow, Jan Czarnowski, Andrea Nicastro +2
The best way to combine the results of deep learning with standard 3D reconstruction pipelines remains an open problem. While systems that pass the output of traditional multi-view…
DeepFusion: Real-Time Dense 3D Reconstruction for Monocular SLAM using Single-View Depth and Gradient Predictions
Tristan Laidlow, Jan Czarnowski, Stefan Leutenegger
While the keypoint-based maps created by sparse monocular simultaneous localisation and mapping (SLAM) systems are useful for camera tracking, dense 3D reconstructions may be desir…
CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations
Hidenobu Matsuki, Raluca Scona, Jan Czarnowski +1
We propose a novel dense mapping framework for sparse visual SLAM systems which leverages a compact scene representation. State-of-the-art sparse visual SLAM systems provide accura…
DeepFactors: Real-Time Probabilistic Dense Monocular SLAM
Jan Czarnowski, Tristan Laidlow, Ronald Clark +1
The ability to estimate rich geometry and camera motion from monocular imagery is fundamental to future interactive robotics and augmented reality applications. Different approache…
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…
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…
Semantic Texture for Robust Dense Tracking
Jan Czarnowski, Stefan Leutenegger, Andrew Davison
We argue that robust dense SLAM systems can make valuable use of the layers of features coming from a standard CNN as a pyramid of `semantic texture' which is suitable for dense al…