arXiv subjects

Stefan Leutenegger

Publications and source records attributed to Stefan Leutenegger.

83 records · Page 5Linked to original sources

arXiv2018

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

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 made by solvers are often not satisfied and many problems are inherently ill-posed. 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. Unlike traditional approaches, the proposed solver requires no hand-crafted regularizers or priors as these are implicitly learned from the data. We apply our method to the problem of motion stereo ie. jointly estimating the motion and scene geometry from pairs of images of a monocular sequence. We show that our learned optimizer is able to efficiently and effectively solve this challenging optimization problem.

cs.CV↗

arXiv2018

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

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). Without a doubt, synthetic imagery bears a vast potential due to scalability in terms of amounts of data obtainable without tedious manual ground truth annotations or measurements. Here, we present a dataset with the aim of providing a higher degree of photo-realism, larger scale, more variability as well as serving a wider range of purposes compared to existing datasets. Our dataset leverages the availability of millions of professional interior designs and millions of production-level furniture and object assets -- all coming with fine geometric details and high-resolution texture. We render high-resolution and high frame-rate video sequences following realistic trajectories while supporting various camera types as well as providing inertial measurements. Together with the release of the dataset, we will make executable program of our interactive simulator software as well as our renderer available at https://interiornetdataset.github.io. To showcase the usability and uniqueness of our dataset, we show benchmarking results of both sparse and dense SLAM algorithms.

cs.CV↗

arXiv2018

Fusion++: Volumetric Object-Level SLAM

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 scene, Mask-RCNN instance segmentations are used to initialise compact per-object Truncated Signed Distance Function (TSDF) reconstructions with object size-dependent resolutions and a novel 3D foreground mask. Reconstructed objects are stored in an optimisable 6DoF pose graph which is our only persistent map representation. Objects are incrementally refined via depth fusion, and are used for tracking, relocalisation and loop closure detection. Loop closures cause adjustments in the relative pose estimates of object instances, but no intra-object warping. Each object also carries semantic information which is refined over time and an existence probability to account for spurious instance predictions. We demonstrate our approach on a hand-held RGB-D sequence from a cluttered office scene with a large number and variety of object instances, highlighting how the system closes loops and makes good use of existing objects on repeated loops. We quantitatively evaluate the trajectory error of our system against a baseline approach on the RGB-D SLAM benchmark, and qualitatively compare reconstruction quality of discovered objects on the YCB video dataset. Performance evaluation shows our approach is highly memory efficient and runs online at 4-8Hz (excluding relocalisation) despite not being optimised at the software level.

cs.CV↗

arXiv2018

Towards an Embodied Semantic Fovea: Semantic 3D scene reconstruction from ego-centric eye-tracker videos

Incorporating the physical environment is essential for a complete understanding of human behavior in unconstrained every-day tasks. This is especially important in ego-centric tasks where obtaining 3 dimensional information is both limiting and challenging with the current 2D video analysis methods proving insufficient. Here we demonstrate a proof-of-concept system which provides real-time 3D mapping and semantic labeling of the local environment from an ego-centric RGB-D video-stream with 3D gaze point estimation from head mounted eye tracking glasses. We augment existing work in Semantic Simultaneous Localization And Mapping (Semantic SLAM) with collected gaze vectors. Our system can then find and track objects both inside and outside the user field-of-view in 3D from multiple perspectives with reasonable accuracy. We validate our concept by producing a semantic map from images of the NYUv2 dataset while simultaneously estimating gaze position and gaze classes from recorded gaze data of the dataset images.

cs.CV↗

arXiv2017

Semantic Texture for Robust Dense Tracking

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. We use a straightforward Lucas-Kanade formulation of image alignment, with a schedule of iterations over the coarse-to-fine levels of a pyramid, and simply replace the usual image pyramid by the hierarchy of convolutional feature maps from a pre-trained CNN. The resulting dense alignment performance is much more robust to lighting and other variations, as we show by camera rotation tracking experiments on time-lapse sequences captured over many hours. Looking towards the future of scene representation for real-time visual SLAM, we further demonstrate that a selection using simple criteria of a small number of the total set of features output by a CNN gives just as accurate but much more efficient tracking performance.

cs.CV↗

arXiv2017

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

We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection, and also for geometric computer vision problems such as optical flow, depth estimation, camera pose estimation, and 3D reconstruction. Random sampling permits virtually unlimited scene configurations, and here we provide a set of 5M rendered RGB-D images from over 15K trajectories in synthetic layouts with random but physically simulated object poses. Each layout also has random lighting, camera trajectories, and textures. The scale of this dataset is well suited for pre-training data-driven computer vision techniques from scratch with RGB-D inputs, which previously has been limited by relatively small labelled datasets in NYUv2 and SUN RGB-D. It also provides a basis for investigating 3D scene labelling tasks by providing perfect camera poses and depth data as proxy for a SLAM system. We host the dataset at http://robotvault.bitbucket.io/scenenet-rgbd.html

cs.CV↗

arXiv2016

A Primer on the Differential Calculus of 3D Orientations

The proper handling of 3D orientations is a central element in many optimization problems in engineering. Unfortunately many researchers and engineers struggle with the formulation of such problems and often fall back to suboptimal solutions. The existence of many different conventions further complicates this issue, especially when interfacing multiple differing implementations. This document discusses an alternative approach which makes use of a more abstract notion of 3D orientations. The relative orientation between two coordinate systems is primarily identified by the coordinate mapping it induces. This is combined with the standard exponential map in order to introduce representation-independent and minimal differentials, which are very convenient in optimization based methods.

cs.RO↗

arXiv2016

SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks

Ever more robust, accurate and detailed mapping using visual sensing has proven to be an enabling factor for mobile robots across a wide variety of applications. For the next level of robot intelligence and intuitive user interaction, maps need extend beyond geometry and appearence - they need to contain semantics. We address this challenge by combining Convolutional Neural Networks (CNNs) and a state of the art dense Simultaneous Localisation and Mapping (SLAM) system, ElasticFusion, which provides long-term dense correspondence between frames of indoor RGB-D video even during loopy scanning trajectories. These correspondences allow the CNN's semantic predictions from multiple view points to be probabilistically fused into a map. 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. We also show that for a smaller reconstruction dataset with larger variation in prediction viewpoint, the improvement over single frame segmentation increases. Our system is efficient enough to allow real-time interactive use at frame-rates of approximately 25Hz.

cs.CV↗

arXiv2016

Deep Learning a Grasp Function for Grasping under Gripper Pose Uncertainty

This paper presents a new method for parallel-jaw grasping of isolated objects from depth images, under large gripper pose uncertainty. Whilst most approaches aim to predict the single best grasp pose from an image, our method first predicts a score for every possible grasp pose, which we denote the grasp function. 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. Therefore, if the single best pose is adjacent to a region of poor grasp quality, that pose will no longer be chosen, and instead a pose will be chosen which is surrounded by a region of high grasp quality. To learn this function, we train a Convolutional Neural Network which takes as input a single depth image of an object, and outputs a score for each grasp pose across the image. Training data for this is generated by use of physics simulation and depth image simulation with 3D object meshes, to enable acquisition of sufficient data without requiring exhaustive real-world experiments. We evaluate with both synthetic and real experiments, and show that the learned grasp score is more robust to gripper pose uncertainty than when this uncertainty is not accounted for.

cs.RO↗

arXiv2016

Pairwise Decomposition of Image Sequences for Active Multi-View Recognition

A multi-view image sequence provides a much richer capacity for object recognition than from a single image. However, most existing solutions to multi-view recognition typically adopt hand-crafted, model-based geometric methods, which do not readily embrace recent trends in deep learning. We propose to bring Convolutional Neural Networks to generic multi-view recognition, by decomposing an image sequence into a set of image pairs, classifying each pair independently, and then learning an object classifier by weighting the contribution of each pair. This allows for recognition over arbitrary camera trajectories, without requiring explicit training over the potentially infinite number of camera paths and lengths. Building these pairwise relationships then naturally extends to the next-best-view problem in an active recognition framework. To achieve this, we train a second Convolutional Neural Network to map directly from an observed image to next viewpoint. Finally, we incorporate this into a trajectory optimisation task, whereby the best recognition confidence is sought for a given trajectory length. We present state-of-the-art results in both guided and unguided multi-view recognition on the ModelNet dataset, and show how our method can be used with depth images, greyscale images, or both.

cs.CV↗

arXiv2015

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

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". These attributes make them, at least in theory, particularly suitable for enabling tasks like navigation and mapping on high speed robotic platforms under challenging lighting conditions, a task which has been particularly challenging for traditional algorithms and camera sensors. Before these tasks become feasible however, progress must be made towards adapting and innovating current RGB-camera-based algorithms to work with event-based cameras. In this paper we present ongoing research investigating two distinct approaches to incorporating event-based cameras for robotic navigation: the investigation of suitable place recognition / loop closure techniques, and the development of efficient neural implementations of place recognition techniques that enable the possibility of place recognition using event-based cameras at very high frame rates using neuromorphic computing hardware.

cs.RO↗