Search Results for author: Stefan Leutenegger

Found 27 papers, 5 papers with code

BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking

no code implementations4 May 2022 Dorian Henning, Tristan Laidlow, Stefan Leutenegger

Through a series of experiments on video sequences of human motion captured by a moving monocular camera, we demonstrate that BodySLAM improves estimates of all human body parameters and camera poses when compared to estimating these separately.

OKVIS2: Realtime Scalable Visual-Inertial SLAM with Loop Closure

no code implementations18 Feb 2022 Stefan Leutenegger

Robust and accurate state estimation remains a challenge in robotics, Augmented, and Virtual Reality (AR/VR), even as Visual-Inertial Simultaneous Localisation and Mapping (VI-SLAM) getting commoditised.

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

no code implementations ICCV 2021 Zoe Landgraf, Raluca Scona, Tristan Laidlow, Stephen James, Stefan Leutenegger, Andrew J. Davison

At test time, our model can generate 3D shape and instance segmentation from a single depth view, probabilistically sampling proposals for the occluded region from the learned latent space.

Instance Segmentation Semantic Segmentation

In-Place Scene Labelling and Understanding with Implicit Scene Representation

no code implementations ICCV 2021 Shuaifeng Zhi, Tristan Laidlow, Stefan Leutenegger, Andrew J. Davison

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.

Denoising Super-Resolution

Deep Probabilistic Feature-metric Tracking

no code implementations31 Aug 2020 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.

Object Tracking

Bundle Adjustment on a Graph Processor

1 code implementation CVPR 2020 Joseph Ortiz, Mark Pupilli, Stefan Leutenegger, Andrew J. Davison

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 massively parallel computation, distributed on-chip memory and very high inter-core communication bandwidth which allows breakthrough performance for message passing algorithms on arbitrary graphs.

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

no code implementations24 Feb 2020 Zoe Landgraf, Fabian Falck, Michael Bloesch, Stefan Leutenegger, Andrew Davison

Generally capable Spatial AI systems must build persistent scene representations where geometric models are combined with meaningful semantic labels.

Towards Bounding-Box Free Panoptic Segmentation

no code implementations18 Feb 2020 Ujwal Bonde, Pablo F. Alcantarilla, Stefan Leutenegger

Our approach is distinct from previous works in panoptic segmentation that rely on a combination of a semantic segmentation network with a computationally costly instance segmentation network based on bounding box proposals, such as Mask R-CNN, to guide the prediction of instance labels using a Mixture-of-Expert (MoE) approach.

Instance Segmentation Panoptic Segmentation

Event-based Vision: A Survey

4 code implementations17 Apr 2019 Guillermo Gallego, Tobi Delbruck, Garrick Orchard, Chiara Bartolozzi, Brian Taba, Andrea Censi, Stefan Leutenegger, Andrew Davison, Joerg Conradt, Kostas Daniilidis, Davide Scaramuzza

Event cameras offer attractive properties compared to traditional cameras: high temporal resolution (in the order of microseconds), very high dynamic range (140 dB vs. 60 dB), low power consumption, and high pixel bandwidth (on the order of kHz) resulting in reduced motion blur.

Event-based vision

SceneCode: Monocular Dense Semantic Reconstruction using Learned Encoded Scene Representations

no code implementations CVPR 2019 Shuaifeng Zhi, Michael Bloesch, Stefan Leutenegger, Andrew J. Davison

Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities.

X-Section: Cross-Section Prediction for Enhanced RGBD Fusion

no code implementations3 Mar 2019 Andrea Nicastro, Ronald Clark, Stefan Leutenegger

Detailed 3D reconstruction is an important challenge with application to robotics, augmented and virtual reality, which has seen impressive progress throughout the past years.

3D Reconstruction

MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM

no code implementations19 Dec 2018 Binbin Xu, Wenbin Li, Dimos Tzoumanikas, Michael Bloesch, Andrew Davison, Stefan Leutenegger

It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the scene.

Frame Instance Segmentation +3

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

no code implementations ECCV 2018 Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J. Davison

In this paper, we propose LS-Net, a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.

InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset

no code implementations3 Sep 2018 Wenbin Li, Sajad Saeedi, John McCormac, Ronald Clark, Dimos Tzoumanikas, Qing Ye, Yuzhong Huang, Rui Tang, Stefan Leutenegger

Datasets have gained an enormous amount of popularity in the computer vision community, from training and evaluation of Deep Learning-based methods to benchmarking Simultaneous Localization and Mapping (SLAM).

Frame Simultaneous Localization and Mapping

Learning to Solve Nonlinear Least Squares for Monocular Stereo

no code implementations ECCV 2018 Ronald Clark, Michael Bloesch, Jan Czarnowski, Stefan Leutenegger, Andrew J. Davison

In this paper, we propose a neural nonlinear least squares optimization algorithm which learns to effectively optimize these cost functions even in the presence of adversities.

Fusion++: Volumetric Object-Level SLAM

no code implementations25 Aug 2018 John McCormac, Ronald Clark, Michael Bloesch, Andrew J. Davison, Stefan Leutenegger

Reconstructed objects are stored in an optimisable 6DoF pose graph which is our only persistent map representation.

Loop Closure Detection

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

1 code implementation CVPR 2018 Michael Bloesch, Jan Czarnowski, Ronald Clark, Stefan Leutenegger, Andrew J. Davison

Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency.

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

2 code implementations3 Apr 2018 Michael Bloesch, Jan Czarnowski, Ronald Clark, Stefan Leutenegger, Andrew J. Davison

Our approach is suitable for use in a keyframe-based monocular dense SLAM system: While each keyframe with a code can produce a depth map, the code can be optimised efficiently jointly with pose variables and together with the codes of overlapping keyframes to attain global consistency.

SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?

no code implementations ICCV 2017 John McCormac, Ankur Handa, Stefan Leutenegger, Andrew J. Davison

We compare the semantic segmentation performance of network weights produced from pre-training on RGB images from our dataset against generic VGG-16 ImageNet weights.

Instance Segmentation Object Detection +4

Semantic Texture for Robust Dense Tracking

no code implementations29 Aug 2017 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 alignment while being much more robust to nuisance factors such as lighting than raw RGB values.

SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth

1 code implementation15 Dec 2016 John McCormac, Ankur Handa, Stefan Leutenegger, Andrew J. Davison

We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories.

3D Reconstruction Depth Estimation +6

SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks

no code implementations16 Sep 2016 John McCormac, Ankur Handa, Andrew Davison, Stefan Leutenegger

This not only produces a useful semantic 3D map, but we also show on the NYUv2 dataset that fusing multiple predictions leads to an improvement even in the 2D semantic labelling over baseline single frame predictions.

Frame

Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty

no code implementations7 Aug 2016 Edward Johns, Stefan Leutenegger, Andrew J. Davison

With this, it is possible to achieve grasping robust to the gripper's pose uncertainty, by smoothing the grasp function with the pose uncertainty function.

Simultaneous Optical Flow and Intensity Estimation From an Event Camera

no code implementations CVPR 2016 Patrick Bardow, Andrew J. Davison, Stefan Leutenegger

In a series of examples, we demonstrate the successful operation of our framework, including in situations where conventional cameras heavily suffer from dynamic range limitations or motion blur.

Frame Optical Flow Estimation

Place Recognition with Event-based Cameras and a Neural Implementation of SeqSLAM

no code implementations18 May 2015 Michael Milford, Hanme Kim, Michael Mangan, Stefan Leutenegger, Tom Stone, Barbara Webb, Andrew Davison

Event-based cameras offer much potential to the fields of robotics and computer vision, in part due to their large dynamic range and extremely high "frame rates".

Frame

Cannot find the paper you are looking for? You can Submit a new open access paper.