Search

Given an unordered list of 2D or 3D point trajectories corrupted by noise and partial observations, in this paper we introduce a framework to simultaneously recover the incomplete motion tracks and group the points into spatially and temporally coherent clusters. This advances existing work, which only addresses partial problems and without considering a unified and unsupervised solution. We cast this problem as a matrix completion one, in which point tracks are arranged into a matrix with the missing entries set as zeros. In order to perform the double clustering, the measurement matrix is assumed to be drawn from a dual union of spatio-temporal subspaces. The bases and the dimensionality for these subspaces, the affinity matrices used to encode the temporal and spatial clusters to which each point belongs, and the non-visible tracks, are then jointly estimated via Augmented Lagrange Multipliers in polynomial time. A thorough evaluation on incomplete motion tracks for multiple object typologies shows that the accuracy of the matrix we recover compares favorably to that obtained with existing low-rank matrix completion methods, specially under noisy measurements. In addition, besides recovering the incomplete tracks, the point trajectories are directly grouped into different object instances, and a number of semantically meaningful temporal primitive actions are automatically discovered., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work has been partially supported by the Spanish State Research Agency through the María de Maeztu Seal of Excellence to IRI MDM-2016-0656, by the Spanish Ministry of Science and Innovation under project HuMoUR TIN2017-90086-R and the Salvador de Madariaga grant PRX19/00626, and by the ERA-net CHIST-ERA project IPALM PCI2019-103386.

We propose an approach to estimating the 3D pose of a hand, possibly handling an object, given a depth image. We show that we can correct the mistakes made by a Convolutional Neural Network trained to predict an estimate of the 3D pose by using a feedback loop. The components of this feedback loop are also Deep Networks, optimized using training data. This approach can be generalized to a hand interacting with an object. Therefore, we jointly estimate the 3D pose of the hand and the 3D pose of the object. Our approach performs en-par with state-of-the-art methods for 3D hand pose estimation, and outperforms state-of-the-art methods for joint hand-object pose estimation when using depth images only. Also, our approach is efficient as our implementation runs in real-time on a single GPU., arXiv admin note: substantial text overlap with arXiv:1609.09698

We explore how a general AI algorithm can be used for 3D scene understanding to reduce the need for training data. More exactly, we propose a modification of the Monte Carlo Tree Search (MCTS) algorithm to retrieve objects and room layouts from noisy RGB-D scans. While MCTS was developed as a game-playing algorithm, we show it can also be used for complex perception problems. Our adapted MCTS algorithm has few easy-to-tune hyperparameters and can optimise general losses. We use it to optimise the posterior probability of objects and room layout hypotheses given the RGB-D data. This results in an analysis-by-synthesis approach that explores the solution space by rendering the current solution and comparing it to the RGB-D observations. To perform this exploration even more efficiently, we propose simple changes to the standard MCTS' tree construction and exploration policy. We demonstrate our approach on the ScanNet dataset. Our method often retrieves configurations that are better than some manual annotations, especially on layouts., Comment: To be presented at CVPR 2021

International audience; We present a method that detects stable keypoints from an event stream at high speed with a low memory footprint. Our key observation connects two points: It should be easier to reconstruct the image gradients rather than the image itself from the events, and the Harris corner detector, one of the most reliable keypoint detectors for short baseline regular images, depends on the image gradients, not the image. We therefore introduce a recurrent convolutional neural network to predict image gradients from events. As image gradients and events are correlated, this prediction task is relatively easy and we can keep this network very small. We train our network solely on synthetic data. Extracting Harris corners from these gradients is then very efficient. Moreover, in contrast to learned methods, we can change the hyperparameters of the detector without retraining. Our experiments confirm that predicting image gradients rather than images is much more efficient, and that our approach predicts stable corner points which are easier to track for a longer time compared to state-of-the-art event-based methods.

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple learning algorithms. Many regress precise geometric quantities, like poses or 3D points, from an input image. This either fails to generalize to new viewpoints or ties the model parameters to a specific scene. In this paper, we go Back to the Feature: we argue that deep networks should focus on learning robust and invariant visual features, while the geometric estimation should be left to principled algorithms. We introduce PixLoc, a scene-agnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. Our approach is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. The system can localize in large environments given coarse pose priors but also improve the accuracy of sparse feature matching by jointly refining keypoints and poses with little overhead. The code will be publicly available at https://github.com/cvg/pixloc., Comment: Accepted to CVPR 2021

International audience; Absolute camera pose estimation is usually addressed by sequentially solving two distinct subproblems: First a feature matching problem that seeks to establish putative 2D-3D correspondences, and then a Perspective-n-Point problem that minimizes, w.r.t. the camera pose, the sum of socalled Reprojection Errors (RE). We argue that generating putative 2D-3D correspondences 1) leads to an important loss of information that needs to be compensated as far as possible, within RE, through the choice of a robust loss and the tuning of its hyperparameters and 2) may lead to an RE that conveys erroneous data to the pose estimator. In this paper, we introduce the Neural Reprojection Error (NRE) as a substitute for RE. NRE allows to rethink the camera pose estimation problem by merging it with the feature learning problem, hence leveraging richer information than 2D-3D correspondences and eliminating the need for choosing a robust loss and its hyperparameters. Thus NRE can be used as training loss to learn image descriptors tailored for pose estimation. We also propose a coarse-to-fine optimization method able to very efficiently minimize a sum of NRE terms w.r.t. the camera pose. We experimentally demonstrate that NRE is a good substitute for RE as it significantly improves both the robustness and the accuracy of the camera pose estimate while being computationally and memory highly efficient. From a broader point of view, we believe this new way of merging deep learning and 3D geometry may be useful in other computer vision applications. Source code and model weights will be made available at hugogermain.com/nre.

We present a novel method for predicting accurate depths from monocular images with high efficiency. This optimal efficiency is achieved by exploiting wavelet decomposition, which is integrated in a fully differentiable encoder-decoder architecture. We demonstrate that we can reconstruct high-fidelity depth maps by predicting sparse wavelet coefficients. In contrast with previous works, we show that wavelet coefficients can be learned without direct supervision on coefficients. Instead we supervise only the final depth image that is reconstructed through the inverse wavelet transform. We additionally show that wavelet coefficients can be learned in fully self-supervised scenarios, without access to ground-truth depth. Finally, we apply our method to different state-of-the-art monocular depth estimation models, in each case giving similar or better results compared to the original model, while requiring less than half the multiply-adds in the decoder network. Code at https://github.com/nianticlabs/wavelet-monodepth, CVPR 2021

International audience; We present an approach for detecting and estimating the 3D poses of objects in images that requires only an untextured CAD model and no training phase for new objects. Our approach combines Deep Learning and 3D geometry: It relies on an embedding of local 3D geometry to match the CAD models to the input images. For points at the surface of objects, this embedding can be computed directly from the CAD model; for image locations, we learn to predict it from the image itself. This establishes correspondences between 3D points on the CAD model and 2D locations of the input images. However, many of these correspondences are ambiguous as many points may have similar local geometries. We show that we can use Mask-RCNN in a class-agnostic way to detect the new objects without retraining and thus drastically limit the number of possible correspondences. We can then robustly estimate a 3D pose from these discriminative correspondences using a RANSAC-like algorithm. We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects. Our experiments show that our method is on par or better than previous methods.

[EN] Whole brain segmentation of fine-grained structures using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a single convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called AssemblyNet, made of two "assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions, unseen problem and reaching a relevant consensus. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an "amendment" procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. During our validation, AssemblyNet showed competitive performance compared to state-of-the-art methods such as U-Net, Joint label fusion and SLANT. Moreover, we investigated the scan-rescan consistency and the robustness to disease effects of our method. These experiences demonstrated the reliability of AssemblyNet. Finally, we showed the interest of using semi-supervised learning to improve the performance of our method., This work benefited from the support of the project DeepvolBrain of the French National Research Agency (ANR-18-CE45-0013). This study was achieved within the context of the Laboratory of Excellence TRAIL ANR-10-LABX-57 for the BigDataBrain project. Moreover, we thank the Investments for the future Program IdEx Bordeaux (ANR-10-IDEX-0 3-02, HL-MRI Project), Cluster of excellence CPU and the CNRS/INSERM for the DeepMultiBrain project. This study has been also supported by the DPI2017-87743-R grant from the Spanish Ministerio de Economia, Industria Competitividad. The C-MIND data used in the preparation of this article were obtained from the C-MIND Data Repository (accessed in Feb 2015) created by the C-MIND study of Normal Brain Development. This is a multisite, longitudinal study of typically developing children from ages newborn through young adulthood conducted by Cincinnati Children's Hospital Medical Center and UCLA and supported by the National Institute of Child Health and Human Development (Contract #s HHSN275200900018C). The NDAR data used in the preparation of this manuscript were obtained from the NIH-supported National Database for Autism Research (NDAR). This is a multisite, longitudinal study of typically developing children from ages newborn through young adulthood conducted by the Brain Development Cooperative Group and supported by the National Institute of Child Health and Human Development, the National Institute on Drug Abuse, the National Institute of Mental Health, and the National Institute of Neurological Disorders and Stroke (Contract #s N01- HD02-3343, N01-MH9-0002, and N01-NS-9-2314, -2315, -2316, -2317, -2319 and -2320). A listing of the participating sites and a complete listing of the study investigators can be found at http://pediatricmri.nih.gov/nihpd/info/participating_centers.html. The ADNI data used in the preparation of this manuscript were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904). ADNI data are disseminated by the Laboratory for NeuroImaging at the University of California, Los Angeles. This research was also supported by NIH grants P30AG010129, K01 AG030514 and the Dana Foundation. The OASIS data used in the preparation of this manuscript were obtained from the OASIS project funded by grants P50 AG05681, P01 AG03991, R01 AG021910, P50 MH071616, U24 RR021382, R01 MH56584. The AIBL data used in the preparation of this manuscript were obtained from the AIBL study of ageing funded by the Common-wealth Scientific Industrial Research Organization (CSIRO; a publicly funded government research organization), Science Industry Endowment Fund, National Health and Medical Research Council of Australia (project grant 1011689), Alzheimer's Association, Alzheimer's Drug Discovery Foundation, and an anonymous foundation. The ICBM data used in the preparation of this manuscript were supported by Human Brain Project grant PO1MHO52176-11 (ICBM, P.I. Dr John Mazziotta) and Canadian Institutes of Health Research grant MOP-34996. The IXI data used in the preparation of this manuscript were supported by the U.K. Engineering and Physical Sciences Research Council (EPSRC) GR/S21533/02. ABIDE primary support for the work by Adriana Di Martino was provided by the NIMH (K23MH087770) and the Leon Levy Foundation. Primary support for the work by Michael P. Milham and the INDI team was provided by gifts from Joseph P. Healy and the Stavros Niarchos Foundation to the Child Mind Institute, as well as by an NIMH award to MPM (R03MH096321).

Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours for the occlusion boundaries in the input image. This is unfortunate as occlusion boundaries are important cues to recognize objects, and as we show, may lead to a way to discover new objects from scene reconstruction. To improve predicted depth maps, recent methods rely on various forms of filtering or predict an additive residual depth map to refine a first estimate. We instead learn to predict, given a depth map predicted by some reconstruction method, a 2D displacement field able to re-sample pixels around the occlusion boundaries into sharper reconstructions. Our method can be applied to the output of any depth estimation method, in an end-to-end trainable fashion. For evaluation, we manually annotated the occlusion boundaries in all the images in the test split of popular NYUv2-Depth dataset. We show that our approach improves the localization of occlusion boundaries for all state-of-the-art monocular depth estimation methods that we could evaluate, without degrading the depth accuracy for the rest of the images., Comment: Accepted to CVPR 2020

We propose a method for annotating images of a hand manipulating an object with the 3D poses of both the hand and the object, together with a dataset created using this method. Our motivation is the current lack of annotated real images for this problem, as estimating the 3D poses is challenging, mostly because of the mutual occlusions between the hand and the object. To tackle this challenge, we capture sequences with one or several RGB-D cameras and jointly optimize the 3D hand and object poses over all the frames simultaneously. This method allows us to automatically annotate each frame with accurate estimates of the poses, despite large mutual occlusions. With this method, we created HO-3D, the first markerless dataset of color images with 3D annotations for both the hand and object. This dataset is currently made of 77,558 frames, 68 sequences, 10 persons, and 10 objects. Using our dataset, we develop a single RGB image-based method to predict the hand pose when interacting with objects under severe occlusions and show it generalizes to objects not seen in the dataset., Comment: Accepted to CVPR2020

We propose a novel method to efficiently estimate the spatial layout of a room from a single monocular RGB image. As existing approaches based on low-level feature extraction, followed by a vanishing point estimation are very slow and often unreliable in realistic scenarios, we build on semantic segmentation of the input image. To obtain better segmentations, we introduce a robust, accurate and very efficient hypothesize-and-test scheme. The key idea is to use three segmentation hypotheses, each based on a different number of visible walls. For each hypothesis, we predict the image locations of the room corners and select the hypothesis for which the layout estimated from the room corners is consistent with the segmentation. We demonstrate the efficiency and robustness of our method on three challenging benchmark datasets, where we significantly outperform the state-of-the-art., Accepted: Winter Conference on Applications of Computer Vision (WACV) 2020

Establishing robust and accurate correspondences is a fundamental backbone to many computer vision algorithms. While recent learning-based feature matching methods have shown promising results in providing robust correspondences under challenging conditions, they are often limited in terms of precision. In this paper, we introduce S2DNet, a novel feature matching pipeline, designed and trained to efficiently establish both robust and accurate correspondences. By leveraging a sparse-to-dense matching paradigm, we cast the correspondence learning problem as a supervised classification task to learn to output highly peaked correspondence maps. We show that S2DNet achieves state-of-the-art results on the HPatches benchmark, as well as on several long-term visual localization datasets.

We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images and synthetic renderings in the RGB or mask space, we compare them in a feature space optimized for 3D pose refinement. Second, we introduce a novel differentiable renderer that learns to approximate the rasterization backward pass from data instead of relying on a hand-crafted algorithm. For this purpose, we predict deep cross-domain correspondences between RGB images and 3D model renderings in the form of what we call geometric correspondence fields. These correspondence fields serve as pixel-level gradients which are analytically propagated backward through the rendering pipeline to perform a gradient-based optimization directly on the 3D pose. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.

We study how well different types of approaches generalise in the task of 3D hand pose estimation under single hand scenarios and hand-object interaction. We show that the accuracy of state-of-the-art methods can drop, and that they fail mostly on poses absent from the training set. Unfortunately, since the space of hand poses is highly dimensional, it is inherently not feasible to cover the whole space densely, despite recent efforts in collecting large-scale training datasets. This sampling problem is even more severe when hands are interacting with objects and/or inputs are RGB rather than depth images, as RGB images also vary with lighting conditions and colors. To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set. More exactly, HANDS'19 is designed (a) to evaluate the influence of both depth and color modalities on 3D hand pose estimation, under the presence or absence of objects; (b) to assess the generalisation abilities w.r.t. four main axes: shapes, articulations, viewpoints, and objects; (c) to explore the use of a synthetic hand model to fill the gaps of current datasets. Through the challenge, the overall accuracy has dramatically improved over the baseline, especially on extrapolation tasks, from 27mm to 13mm mean joint error. Our analyses highlight the impacts of: Data pre-processing, ensemble approaches, the use of a parametric 3D hand model (MANO), and different HPE methods/backbones., Comment: European Conference on Computer Vision (ECCV), 2020

We present a novel method to reconstruct the 3D layout of a room—walls, floors, ceilings—from a single perspective view in challenging conditions, by contrast with previous single-view methods restricted to cuboid-shaped layouts. This input view can consist of a color image only, but considering a depth map results in a more accurate reconstruction. Our approach is formalized as solving a constrained discrete optimization problem to find the set of 3D polygons that constitute the layout. In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate. As no dataset was available to evaluate our method quantitatively, we created one together with several appropriate metrics. Our dataset consists of 293 images from ScanNet, which we annotated with precise 3D layouts. It offers three times more samples than the popular NYUv2 303 benchmark, and a much larger variety of layouts.

We present an algorithm for estimating the pose of a rigid object in real-time under challenging conditions. Our method effectively handles poorly textured objects in cluttered, changing environments, even when their appearance is corrupted by large occlusions, and it relies on grayscale images to handle metallic environments on which depth cameras would fail. As a result, our method is suitable for practical Augmented Reality applications including industrial environments. At the core of our approach is a novel representation for the 3D pose of object parts: We predict the 3D pose of each part in the form of the 2D projections of a few control points. The advantages of this representation is three-fold: We can predict the 3D pose of the object even when only one part is visible; when several parts are visible, we can easily combine them to compute a better pose of the object; the 3D pose we obtain is usually very accurate, even when only few parts are visible. We show how to use this representation in a robust 3D tracking framework. In addition to extensive comparisons with the state-of-the-art, we demonstrate our method on a practical Augmented Reality application for maintenance assistance in the ATLAS particle detector at CERN.

We introduce SharpNet, a method that predicts an accurate depth map for an input color image, with a particular attention to the reconstruction of occluding contours: Occluding contours are an important cue for object recognition, and for realistic integration of virtual objects in Augmented Reality, but they are also notoriously difficult to reconstruct accurately. For example, they are a challenge for stereo-based reconstruction methods, as points around an occluding contour are visible in only one image. Inspired by recent methods that introduce normal estimation to improve depth prediction, we introduce a novel term that constrains depth and occluding contours predictions. Since ground truth depth is difficult to obtain with pixel-perfect accuracy along occluding contours, we use synthetic images for training, followed by fine-tuning on real data. We demonstrate our approach on the challenging NYUv2-Depth dataset, and show that our method outperforms the state-of-the-art along occluding contours, while performing on par with the best recent methods for the rest of the images. Its accuracy along the occluding contours is actually better than the `ground truth' acquired by a depth camera based on structured light. We show this by introducing a new benchmark based on NYUv2-Depth for evaluating occluding contours in monocular reconstruction, which is our second contribution., Comment: Accepted at ICCV "3D Reconstruction in the Wild" workshop

International audience; Whole brain segmentation using deep learning (DL) is a very challenging task since the number of anatomical labels is very high compared to the number of available training images. To address this problem, previous DL methods proposed to use a global convolution neural network (CNN) or few independent CNNs. In this paper, we present a novel ensemble method based on a large number of CNNs processing different overlapping brain areas. Inspired by parliamentary decision-making systems, we propose a framework called Assem-blyNet, made of two "assemblies" of U-Nets. Such a parliamentary system is capable of dealing with complex decisions and reaching a consensus quickly. AssemblyNet introduces sharing of knowledge among neighboring U-Nets, an "amendment" procedure made by the second assembly at higher-resolution to refine the decision taken by the first one, and a final decision obtained by majority voting. When using the same 45 training images, AssemblyNet outperforms global U-Net by 28% in terms of the Dice metric, patch-based joint label fusion by 15% and SLANT-27 by 10%. Finally, AssemblyNet demonstrates high capacity to deal with limited training data to achieve whole brain segmentation in practical training and testing times.

We propose LU-Net -- for LiDAR U-Net, a new method for the semantic segmentation of a 3D LiDAR point cloud. Instead of applying some global 3D segmentation method such as PointNet, we propose an end-to-end architecture for LiDAR point cloud semantic segmentation that efficiently solves the problem as an image processing problem. We first extract high-level 3D features for each point given its 3D neighbors. Then, these features are projected into a 2D multichannel range-image by considering the topology of the sensor. Thanks to these learned features and this projection, we can finally perform the segmentation using a simple U-Net segmentation network, which performs very well while being very efficient. In this way, we can exploit both the 3D nature of the data and the specificity of the LiDAR sensor. This approach outperforms the state-of-the-art by a large margin on the KITTI dataset, as our experiments show. Moreover, this approach operates at 24fps on a single GPU. This is above the acquisition rate of common LiDAR sensors which makes it suitable for real-time applications., 9 pages, 9 figures. arXiv admin note: substantial text overlap with arXiv:1905.08748

International audience; We propose a novel approach to feature point matching, suitable for robust and accurate outdoor visual localization in long-term scenarios. Given a query image, we first match it against a database of registered reference images, using recent retrieval techniques. This gives us a first estimate of the camera pose. To refine this estimate, like previous approaches, we match 2D points across the query image and the retrieved reference image. This step, however, is prone to fail as it is still very difficult to detect and match sparse feature points across images captured in potentially very different conditions. Our key contribution is to show that we need to extract sparse feature points only in the retrieved reference image: We then search for the corresponding 2D locations in the query image exhaustively. This search can be performed efficiently using convolutional operations , and robustly by using hypercolumn descriptors, i.e. image features computed for retrieval. We refer to this method as 'Sparse-to-Dense Hypercolumn Matching'. Because we know the 3D locations of the sparse feature points in the reference images thanks to an offline reconstruction stage, it is then possible to accurately estimate the camera pose from these matches. Our experiments show that this method allows us to outperform the state-of-the-art on several challenging outdoor datasets.

Objects with symmetries are common in our daily life and in industrial contexts, but are often ignored in the recent literature on 6D pose estimation from images. In this paper, we study in an analytical way the link between the symmetries of a 3D object and its appearance in images. We explain why symmetrical objects can be a challenge when training machine learning algorithms that aim at estimating their 6D pose from images. We propose an efficient and simple solution that relies on the normalization of the pose rotation. Our approach is general and can be used with any 6D pose estimation algorithm. Moreover, our method is also beneficial for objects that are 'almost symmetrical', i.e. objects for which only a detail breaks the symmetry. We validate our approach within a Faster-RCNN framework on a synthetic dataset made with objects from the T-Less dataset, which exhibit various types of symmetries, as well as real sequences from T-Less., Comment: International Conference on 3D Vision

We present a novel approach to the detection and 3D pose estimation of objects in color images. Its main contribution is that it does not require any training phases nor data for new objects, while state-of-the-art methods typically require hours of training time and hundreds of training registered images. Instead, our method relies only on the objects' geometries. Our method focuses on objects with prominent corners, which covers a large number of industrial objects. We first learn to detect object corners of various shapes in images and also to predict their 3D poses, by using training images of a small set of objects. To detect a new object in a given image, we first identify its corners from its CAD model; we also detect the corners visible in the image and predict their 3D poses. We then introduce a RANSAC-like algorithm that robustly and efficiently detects and estimates the object's 3D pose by matching its corners on the CAD model with their detected counterparts in the image. Because we also estimate the 3D poses of the corners in the image, detecting only 1 or 2 corners is sufficient to estimate the pose of the object, which makes the approach robust to occlusions. We finally rely on a final check that exploits the full 3D geometry of the objects, in case multiple objects have the same corner spatial arrangement. The advantages of our approach make it particularly attractive for industrial contexts, and we demonstrate our approach on the challenging T-LESS dataset.

We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions. Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range. However, the properties of event-based data are very different compared to standard intensity images, and simple extensions of corner detection methods designed for these images do not perform well on event-based data. We first introduce an efficient way to compute a time surface that is invariant to the speed of the objects. We then show that we can train a Random Forest to recognize events generated by a moving corner from our time surface. Random Forests are also extremely efficient, and therefore a good choice to deal with the high capture frequency of event-based cameras ---our implementation processes up to 1.6Mev/s on a single CPU. Thanks to our time surface formulation and this learning approach, our method is significantly more robust to abrupt changes of direction of the corners compared to previous ones. Our method also naturally assigns a confidence score for the corners, which can be useful for postprocessing. Moreover, we introduce a high-resolution dataset suitable for quantitative evaluation and comparison of corner detection methods for event-based cameras. We call our approach SILC, for Speed Invariant Learned Corners, and compare it to the state-of-the-art with extensive experiments, showing better performance., 8 pages, 7 figures, accepted at CVPR 2019

This report outlines the proceedings of the Fourth International Workshop on Observing and Understanding Hands in Action (HANDS 2018). The fourth instantiation of this workshop attracted significant interest from both academia and the industry. The program of the workshop included regular papers that are published as the workshop’s proceedings, extended abstracts, invited posters, and invited talks. Topics of the submitted works and invited talks and posters included novel methods for hand pose estimation from RGB, depth, or skeletal data, datasets for special cases and real-world applications, and techniques for hand motion re-targeting and hand gesture recognition. The invited speakers are leaders in their respective areas of specialization, coming from both industry and academia. The main conclusions that can be drawn are the turn of the community towards RGB data and the maturation of some methods and techniques, which in turn has led to increasing interest for real-world applications.

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the labeling comes for free, and several approaches have been proposed to combine synthetic and real images for training. In this paper, we evaluate if ‘freezing’ the layers responsible for feature extraction to generic layers pre-trained on real images, and training only the remaining layers with plain OpenGL rendering may allow for training with synthetic images only. Our experiments with very recent deep architectures for object recognition (Faster-RCNN, R-FCN, Mask-RCNN) and image feature extractors (InceptionResnet and Resnet) show this simple approach performs surprisingly well.

This document summarizes the 4th International Workshop on Recovering 6D Object Pose which was organized in conjunction with ECCV 2018 in Munich. The workshop featured four invited talks, oral and poster presentations of accepted workshop papers, and an introduction of the BOP benchmark for 6D object pose estimation. The workshop was attended by 100+ people working on relevant topics in both academia and industry who shared up-to-date advances and discussed open problems.

We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level representation in the form of location fields from which we compute pose invariant 3D shape descriptors. Location fields encode correspondences between 2D pixels and 3D surface coordinates and, thus, explicitly capture 3D shape and 3D pose information without appearance variations which are irrelevant for the task. This early fusion of 3D models and RGB images results in three main advantages: First, the bottleneck location field prediction acts as a regularizer during training. Second, major parts of the system benefit from training on a virtually infinite amount of synthetic data. Finally, the predicted location fields are visually interpretable and unblackbox the system. We evaluate our proposed approach on three challenging real-world datasets (Pix3D, Comp, and Stanford) with different object categories and significantly outperform the state-of-the-art by up to 20% absolute in multiple 3D retrieval metrics., Accepted to International Conference on 3D Vision (3DV) 2019 (Oral)

To make Robotics and Augmented Reality applications robust to illumination changes, the current trend is to train a Deep Network with training images captured under many different lighting conditions. Unfortunately, creating such a training set is a very unwieldy and complex task. We therefore propose a novel illumination normalization method that can easily be used for different problems with challenging illumination conditions. Our preliminary experiments show that among current normalization methods, the Difference-of Gaussians method remains a very good baseline, and we introduce a novel illumination normalization model that generalizes it. Our key insight is then that the normalization parameters should depend on the input image, and we aim to train a Convolutional Neural Network to predict these parameters from the input image. This, however, cannot be done in a supervised manner, as the optimal parameters are not known a priori. We thus designed a method to train this network jointly with another network that aims to recognize objects under different illuminations: The latter network performs well when the former network predicts good values for the normalization parameters. We show that our method significantly outperforms standard normalization methods and would also be appear to be universal since it does not have to be re-trained for each new application. Our method improves the robustness to light changes of state-of-the-art 3D object detection and face recognition methods., Comment: This version corresponds to the pre-print of the paper accepted for Computer Vision and Image Understanding (CVIU). arXiv admin note: substantial text overlap with arXiv:1708.09633

We present a real-time method for detecting deformable surfaces, with no need whatsoever for a priori pose knowledge. Our method starts from a set of wide baseline point matches between an undeformed image of the object and the image in which it is to be detected. The matches are used not only to detect but also to compute a precise mapping from one to the other. The algorithm is robust to large deformations, lighting changes, motion blur, and occlusions. It runs at 10 frames per second on a 2.8 GHz PC.We demonstrate its applicability by using it to realistically modify the texture of a deforming surface and to handle complex illumination effects. Combining deformable meshes with a well designed robust estimator is key to dealing with the large number of parameters involved in modeling deformable surfaces and rejecting erroneous matches for error rates of more than 90%, which is considerably more than what is required in practice.

International audience; This chapter discusses the topics for which solutions exist, but which still pose scientific challenges and elements of complexity which would be helpful to discuss in detail. It describes physical models to detect collisions and the problem of the virtual human. The chapter then examines naturalness of the interaction, and proposes an analysis of force feedback. It also discusses the 3D interaction loop as the explanatory framework for the scientific challenges surrounding 3D interaction with virtual or mixed environments. This loop comes from the perception‐action loop, which is very often used in the literature to explain the challenges in virtual reality and augmented reality. In order to improve interaction, different sensory modalities of the user are brought into play: not only sight, but also hearing and touch are fundamental sensory modalities. The chapter finally identifies the scientific challenges related to these different sensory modalities.

International audience; This chapter provides an overview of the current state of augmented reality (AR). It examines the questions of pose computation, which could be used to locate a user in an immersive room or to model the real world, interactions in AR, and the concept of presence in environments that combine real and virtual elements. The chapter describes important innovations in the field of 3D interaction over the last decade. While 3D interaction is less central to AR, its importance is rising nonetheless. From simple applications to visualize digital data that is superimposed on the natural view, RA systems today are offering users increasingly more refined interaction systems in order to enhance usage. The chapter overviews recent developments allowing users to easily and efficiently interact with 3D content displayed on tactile surfaces. In the current interfaces, a trend towards an integration of the interaction styles can be observed.

We propose a simple and efficient method for exploiting synthetic images when training a Deep Network to predict a 3D pose from an image. The ability of using synthetic images for training a Deep Network is extremely valuable as it is easy to create a virtually infinite training set made of such images, while capturing and annotating real images can be very cumbersome. However, synthetic images do not resemble real images exactly, and using them for training can result in suboptimal performance. It was recently shown that for exemplar-based approaches, it is possible to learn a mapping from the exemplar representations of real images to the exemplar representations of synthetic images. In this paper, we show that this approach is more general, and that a network can also be applied after the mapping to infer a 3D pose: At run time, given a real image of the target object, we first compute the features for the image, map them to the feature space of synthetic images, and finally use the resulting features as input to another network which predicts the 3D pose. Since this network can be trained very effectively by using synthetic images, it performs very well in practice, and inference is faster and more accurate than with an exemplar-based approach. We demonstrate our approach on the LINEMOD dataset for 3D object pose estimation from color images, and the NYU dataset for 3D hand pose estimation from depth maps. We show that it allows us to outperform the state-of-the-art on both datasets., CVPR 2018

International audience; We propose an efficient physics-based method for dexterous 'real hand'-'virtual object' interaction in Virtual Reality environments. Our method is based on the Coulomb friction model, and we show how to efficiently implement it in a commodity VR engine for real-time performance. This model enables very convincing simulations of many types of actions such as pushing, pulling, grasping, or even dexterous manipulations such as spinning objects between fingers without restrictions on the objects' shapes or hand poses. Because it is an analytic model, we do not require any prerecorded data, in contrast to previous methods. For the evaluation of our method, we conduction a pilot study that shows that our method is perceived more realistic and natural, and allows for more diverse interactions. Further, we evaluate the computational complexity of our method to show real-time performance in VR environments.

We propose a scalable, efficient and accurate approach to retrieve 3D models for objects in the wild. Our contribution is twofold. We first present a 3D pose estimation approach for object categories which significantly outperforms the state-of-the-art on Pascal3D+. Second, we use the estimated pose as a prior to retrieve 3D models which accurately represent the geometry of objects in RGB images. For this purpose, we render depth images from 3D models under our predicted pose and match learned image descriptors of RGB images against those of rendered depth images using a CNN-based multi-view metric learning approach. In this way, we are the first to report quantitative results for 3D model retrieval on Pascal3D+, where our method chooses the same models as human annotators for 50% of the validation images on average. In addition, we show that our method, which was trained purely on Pascal3D+, retrieves rich and accurate 3D models from ShapeNet given RGB images of objects in the wild., Comment: Accepted to Conference on Computer Vision and Pattern Recognition (CVPR) 2018

We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images., ACCV 2018 (oral)

We introduce a novel method for robust and accurate 3D object pose estimation from a single color image under large occlusions. Following recent approaches, we first predict the 2D projections of 3D points related to the target object and then compute the 3D pose from these correspondences using a geometric method. Unfortunately, as the results of our experiments show, predicting these 2D projections using a regular CNN or a Convolutional Pose Machine is highly sensitive to partial occlusions, even when these methods are trained with partially occluded examples. Our solution is to predict heatmaps from multiple small patches independently and to accumulate the results to obtain accurate and robust predictions. Training subsequently becomes challenging because patches with similar appearances but different positions on the object correspond to different heatmaps. However, we provide a simple yet effective solution to deal with such ambiguities. We show that our approach outperforms existing methods on two challenging datasets: The Occluded LineMOD dataset and the YCB-Video dataset, both exhibiting cluttered scenes with highly occluded objects. Project website: https://www.tugraz.at/institute/icg/research/team-lepetit/research-projects/robust-object-pose-estimation/

International audience; Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convo-lutional Neural Network to directly regress from an image to a 3D pose, which ignores the dependencies between human joints, or model these dependencies via a max-margin structured learning framework, which involves a high computational cost at inference time. In this paper, we introduce a Deep Learning regression architecture for structured prediction of 3D human pose from monocular images or 2D joint location heatmaps that relies on an overcomplete autoencoder to learn a high-dimensional latent pose representation and accounts for joint dependencies. We further propose an efficient Long Short-Term Memory (LSTM) network to enforce temporal consistency on 3D pose predictions. We demonstrate that our approach achieves state-of-the-art performance both in terms of structure preservation and prediction accuracy on standard 3D human pose estimation benchmarks.

Trabajo presentado en la IEEE/CVF Conference on Computer Vision and Pattern Recognition, celebrada en Salt Lake City (UT, USA), del 18 al 23 de junio de 2018, We propose a method for predicting the 3D shape of a deformable surface from a single view. By contrast with previous approaches, we do not need a pre-registered template of the surface, and our method is robust to the lack of texture and partial occlusions. At the core of our approach is a geometry-aware deep architecture that tackles the problem as usually done in analytic solutions: first perform 2D detection of the mesh and then estimate a 3D shape that is geometrically consistent with the image. We train this architecture in an end-to-end manner using a large dataset of synthetic renderings of shapes under different levels of deformation, material properties, textures and lighting conditions. We evaluate our approach on a test split of this dataset and available real benchmarks, consistently improving state-of-the-art solutions with a significantly lower computational time., This work is supported in part by a Google Faculty Research Award, by the Spanish Ministry of Science and Innovation under projects HuMoUR TIN2017- 90086-R, ColRobTransp DPI2016-78957 and Mar´ıa de Maeztu Seal of Excellence MDM-2016-0656; and by the EU project AEROARMS ICT-2014-1-644271. We also thank Nvidia for hardware donation.

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outliers, while simultaneously using them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than directly on the image, and is thus simple and small. We introduce a novel normalization technique, called Context Normalization, which allows us to process each data point separately while imbuing it with global information, and also makes the network invariant to the order of the correspondences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data., CVPR 2018 (Oral)

We present a method for large-scale geo-localization and global tracking of mobile devices in urban outdoor environments. In contrast to existing methods, we instantaneously initialize and globally register a SLAM map by localizing the first keyframe with respect to widely available untextured 2.5D maps. Given a single image frame and a coarse sensor pose prior, our localization method estimates the absolute camera orientation from straight line segments and the translation by aligning the city map model with a semantic segmentation of the image. We use the resulting 6DOF pose, together with information inferred from the city map model, to reliably initialize and extend a 3D SLAM map in a global coordinate system, applying a model-supported SLAM mapping approach. We show the robustness and accuracy of our localization approach on a challenging dataset, and demonstrate unconstrained global SLAM mapping and tracking of arbitrary camera motion on several sequences.

Learning filters to produce sparse image representations in terms of over-complete dictionaries has emerged as a powerful way to create image features for many different purposes. Unfortunately, these filters are usually both numerous and non-separable, making their use computationally expensive. In this paper, we show that such filters can be computed as linear combinations of a smaller number of separable ones, thus greatly reducing the computational complexity at no cost in terms of performance. This makes filter learning approaches practical even for large images or 3D volumes, and we show that we significantly outperform state-of-the-art methods on the curvilinear structure extraction task, in terms of both accuracy and speed. Moreover, our approach is general and can be used on generic convolutional filter banks to reduce the complexity of the feature extraction step.

We introduce a large-scale RGBD hand segmentation dataset, with detailed and automatically generated high-quality ground-truth annotations. Existing real-world datasets are limited in quantity due to the difficulty in manually annotating ground-truth labels. By leveraging a pair of brightly colored gloves and an RGBD camera, we propose an acquisition pipeline that eases the task of annotating very large datasets with minimal human intervention. We then quantify the importance of a large annotated dataset in this domain, and compare the performance of existing datasets in the training of deep-learning architectures. Finally, we propose a novel architecture employing strided convolution/deconvolutions in place of max-pooling and unpooling layers. Our variant outperforms baseline architectures while remaining computationally efficient at inference time. Source and datasets will be made publicly available.

DeepPrior is a simple approach based on Deep Learning that predicts the joint 3D locations of a hand given a depth map. Since its publication early 2015, it has been outperformed by several impressive works. Here we show that with simple improvements: adding ResNet layers, data augmentation, and better initial hand localization, we achieve better or similar performance than more sophisticated recent methods on the three main benchmarks (NYU, ICVL, MSRA) while keeping the simplicity of the original method. Our new implementation is available at https://github.com/moberweger/deep-prior-pp ., To appear in ICCV Workshops 2017

We present an efficient method for geolocalization in urban environments starting from a coarse estimate of the location provided by a GPS and using a simple untextured 2.5D model of the surrounding buildings. Our key contribution is a novel efficient and robust method to optimize the pose: We train a Deep Network to predict the best direction to improve a pose estimate, given a semantic segmentation of the input image and a rendering of the buildings from this estimate. We then iteratively apply this CNN until converging to a good pose. This approach avoids the use of reference images of the surroundings, which are difficult to acquire and match, while 2.5D models are broadly available. We can therefore apply it to places unseen during training.

We show how to use simple 2.5D maps of buildings and recent advances in image segmentation and machine learning to geo-localize an input image of an urban scene: We first extract the facades of the buildings and their edges from the image, and then look for the orientation and location that align a 3D rendering of the map with these segments. We discuss how to use a 3D tracking system to acquire the data required for training the segmentation method, the segmentation itself, and how we use the segmentations to evaluate the quality of the alignment.