Search

We propose a novel approach to the real-time landing site detection and assessment in unconstrained man-made environments using passive sensors. Because this task must be performed in a few seconds or less, existing methods are often limited to simple local intensity and edge variation cues. By contrast, we show how to efficiently take into account the potential sites' global shape, which is a critical cue in man-made scenes. Our method relies on a new segmentation algorithm and shape regularity measure to look for polygonal regions in video sequences. In this way, we enforce both temporal consistency and geometric regularity, resulting in very reliable and consistent detections. We demonstrate our approach for the detection of landable sites such as rural fields, building rooftops and runways from color and infrared monocular sequences significantly outperforming the state-of-the-art.

This thesis aims at facilitating image segmentation objectives for both computer vision and medical applications. Building on the framework of decision forests, we (i) introduce an efficient and generic scale-adaptive forest training scheme for automatic image understanding, (ii) entangle segmentation with image exploration to examine large digital slides in histopathology, and (iii) model the segmentation task as a 20 Questions game towards hands-free human-computer interactions., Diese Dissertation fokussiert sich auf Bildsegmentierung für allgemeines Bildverstehen und medizinische Anwendungen. Wir führen drei auf Random Forests basierende Beiträge ein: (i) eine Trainingsmethode, die informative visuelle Spannbreiten automatisch entdeckt, (ii) eine mit der Segmentierung kombinierten Navigationsstrategie durch riesige histologische Bilder, und (iii) eine Auffassung des Segmentierungsprozesses als ein „Wer bin ich?“-Spiel für handfreie Interaktionen mit einem Benutzer.

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, 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 {it 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., Peer Reviewed, Postprint (author's final draft)

This thesis aims at facilitating image segmentation objectives for both computer vision and medical applications. Building on the framework of decision forests, we (i) introduce an efficient and generic scale-adaptive forest training scheme for automatic image understanding, (ii) entangle segmentation with image exploration to examine large digital slides in histopathology, and (iii) model the segmentation task as a 20 Questions game towards hands-free human-computer interactions., Diese Dissertation fokussiert sich auf Bildsegmentierung für allgemeines Bildverstehen und medizinische Anwendungen. Wir führen drei auf Random Forests basierende Beiträge ein: (i) eine Trainingsmethode, die informative visuelle Spannbreiten automatisch entdeckt, (ii) eine mit der Segmentierung kombinierten Navigationsstrategie durch riesige histologische Bilder, und (iii) eine Auffassung des Segmentierungsprozesses als ein „Wer bin ich?“-Spiel für handfreie Interaktionen mit einem Benutzer.

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.

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

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views. More exactly, image locations corresponding to the same physical 3D point should all have the same label. We show that introducing such constraints during learning is very effective, even when no manual label is available for a 3D point, and can be done simply by employing techniques from 'general' semi-supervised learning to the context of semantic segmentation. To demonstrate this idea, we use RGB-D image sequences of rigid scenes, for a 4-class segmentation problem derived from the ScanNet dataset. Starting from RGB-D sequences with a few annotated frames, we show that we can incorporate RGB-D sequences without any manual annotations to improve the performance, which makes our approach very convenient. Furthermore, we demonstrate our approach for semantic segmentation of objects on the LabelFusion dataset, where we show that one manually labeled image in a scene is sufficient for high performance on the whole scene., Comment: 8 pages, 5 figures

Outdoor visual localization is a crucial component to many computer vision systems. We propose an approach to localization from images that is designed to explicitly handle the strong variations in appearance happening between daytime and nighttime. As revealed by recent long-term localization benchmarks, both traditional feature-based and retrieval-based approaches still struggle to handle such changes. Our novel localization method combines a state-of-the-art image retrieval architecture with condition-specific sub-networks allowing the computation of global image descriptors that are explicitly dependent of the capturing conditions. We show that our approach improves localization by a factor of almost 300\% compared to the popular VLAD-based methods on nighttime localization.

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., Comment: 11 pages, 1 figure, Discussion of the HANDS 2018 workshop held in conjunction with ECCV 2018

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., Comment: In: Computer Vision - ECCV 2018 Workshops - Munich, Germany, September 8-9 and 14, 2018, Proceedings

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., Comment: ACCV 2018 (oral)

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 {\it 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., Comment: Accepted at CVPR 2018

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

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