arXiv subjects

Didier Stricker

Publications and source records attributed to Didier Stricker.

At least 145 records · Page 8Linked to original sources

arXiv2021

IsMo-GAN: Adversarial Learning for Monocular Non-Rigid 3D Reconstruction

The majority of the existing methods for non-rigid 3D surface regression from monocular 2D images require an object template or point tracks over multiple frames as an input, and are still far from real-time processing rates. In this work, we present the Isometry-Aware Monocular Generative Adversarial Network (IsMo-GAN) - an approach for direct 3D reconstruction from a single image, trained for the deformation model in an adversarial manner on a light-weight synthetic dataset. IsMo-GAN reconstructs surfaces from real images under varying illumination, camera poses, textures and shading at over 250 Hz. In multiple experiments, it consistently outperforms several approaches in the reconstruction accuracy, runtime, generalisation to unknown surfaces and robustness to occlusions. In comparison to the state-of-the-art, we reduce the reconstruction error by 10-30% including the textureless case and our surfaces evince fewer artefacts qualitatively.

cs.CV↗

arXiv2021

Calibration and Auto-Refinement for Light Field Cameras

The ability to create an accurate three-dimensional reconstruction of a captured scene draws attention to the principles of light fields. This paper presents an approach for light field camera calibration and rectification, based on pairwise pattern-based parameters extraction. It is followed by a correspondence-based algorithm for camera parameters refinement from arbitrary scenes using the triangulation filter and nonlinear optimization. The effectiveness of our approach is validated on both real and synthetic data.

cs.CV↗

arXiv2021

Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks

The first phase of table recognition is to detect the tabular area in a document. Subsequently, the tabular structures are recognized in the second phase in order to extract information from the respective cells. Table detection and structural recognition are pivotal problems in the domain of table understanding. However, table analysis is a perplexing task due to the colossal amount of diversity and asymmetry in tables. Therefore, it is an active area of research in document image analysis. Recent advances in the computing capabilities of graphical processing units have enabled deep neural networks to outperform traditional state-of-the-art machine learning methods. Table understanding has substantially benefited from the recent breakthroughs in deep neural networks. However, there has not been a consolidated description of the deep learning methods for table detection and table structure recognition. This review paper provides a thorough analysis of the modern methodologies that utilize deep neural networks. This work provided a thorough understanding of the current state-of-the-art and related challenges of table understanding in document images. Furthermore, the leading datasets and their intricacies have been elaborated along with the quantitative results. Moreover, a brief overview is given regarding the promising directions that can serve as a guide to further improve table analysis in document images.

cs.CV↗

arXiv2021

Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification

Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the criterion of training in a single vehicle: without access to the target distribution of the vehicle the model would be deployed to, neither with access to multiple vehicles during training. We performed an investigation on the SVIRO dataset for occupant classification on the rear bench and propose an autoencoder based approach to improve the transferability. The autoencoder is on par with commonly used classification models when trained from scratch and sometimes out-performs models pre-trained on a large amount of data. Moreover, the autoencoder can transform images from unknown vehicles into the vehicle it was trained on. These results are corroborated by an evaluation on real infrared images from two vehicle interiors.

cs.CV↗

arXiv2021

Guided Table Structure Recognition through Anchor Optimization

This paper presents the novel approach towards table structure recognition by leveraging the guided anchors. The concept differs from current state-of-the-art approaches for table structure recognition that naively apply object detection methods. In contrast to prior techniques, first, we estimate the viable anchors for table structure recognition. Subsequently, these anchors are exploited to locate the rows and columns in tabular images. Furthermore, the paper introduces a simple and effective method that improves the results by using tabular layouts in realistic scenarios. The proposed method is exhaustively evaluated on the two publicly available datasets of table structure recognition i.e ICDAR-2013 and TabStructDB. We accomplished state-of-the-art results on the ICDAR-2013 dataset with an average F-Measure of 95.05$\%$ (94.6$\%$ for rows and 96.32$\%$ for columns) and surpassed the baseline results on the TabStructDB dataset with an average F-Measure of 94.17$\%$ (94.08$\%$ for rows and 95.06$\%$ for columns).

cs.CV↗

arXiv2021

RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut $2^D$-Tree Representation

We propose RPSRNet - a novel end-to-end trainable deep neural network for rigid point set registration. For this task, we use a novel $2^D$-tree representation for the input point sets and a hierarchical deep feature embedding in the neural network. An iterative transformation refinement module in our network boosts the feature matching accuracy in the intermediate stages. We achieve an inference speed of 12-15ms to register a pair of input point clouds as large as 250K. Extensive evaluation on (i) KITTI LiDAR odometry and (ii) ModelNet-40 datasets shows that our method outperforms prior state-of-the-art methods - e.g., on the KITTI data set, DCP-v2 by1.3 and 1.5 times, and PointNetLK by 1.8 and 1.9 times better rotational and translational accuracy respectively. Evaluation on ModelNet40 shows that RPSRNet is more robust than other benchmark methods when the samples contain a significant amount of noise and other disturbances. RPSRNet accurately registers point clouds with non-uniform sampling densities, e.g., LiDAR data, which cannot be processed by many existing deep-learning-based registration methods.

cs.CV↗

arXiv2021

PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN

Instance segmentation of planar regions in indoor scenes benefits visual SLAM and other applications such as augmented reality (AR) where scene understanding is required. Existing methods built upon two-stage frameworks show satisfactory accuracy but are limited by low frame rates. In this work, we propose a real-time deep neural architecture that estimates piece-wise planar regions from a single RGB image. Our model employs a variant of a fast single-stage CNN architecture to segment plane instances. Considering the particularity of the target detected, we propose Fast Feature Non-maximum Suppression (FF-NMS) to reduce the suppression errors resulted from overlapping bounding boxes of planes. We also utilize a Residual Feature Augmentation module in the Feature Pyramid Network (FPN). Our method achieves significantly higher frame-rates and comparable segmentation accuracy against two-stage methods. We automatically label over 70,000 images as ground truth from the Stanford 2D-3D-Semantics dataset. Moreover, we incorporate our method with a state-of-the-art planar SLAM and validate its benefits.

cs.CV↗

arXiv2021

TICaM: A Time-of-flight In-car Cabin Monitoring Dataset

We present TICaM, a Time-of-flight In-car Cabin Monitoring dataset for vehicle interior monitoring using a single wide-angle depth camera. Our dataset addresses the deficiencies of currently available in-car cabin datasets in terms of the ambit of labeled classes, recorded scenarios and provided annotations; all at the same time. We record an exhaustive list of actions performed while driving and provide for them multi-modal labeled images (depth, RGB and IR), with complete annotations for 2D and 3D object detection, instance and semantic segmentation as well as activity annotations for RGB frames. Additional to real recordings, we provide a synthetic dataset of in-car cabin images with same multi-modality of images and annotations, providing a unique and extremely beneficial combination of synthetic and real data for effectively training cabin monitoring systems and evaluating domain adaptation approaches. The dataset is available at https://vizta-tof.kl.dfki.de/.

cs.CV↗

arXiv2021

SALT: A Semi-automatic Labeling Tool for RGB-D Video Sequences

Large labeled data sets are one of the essential basics of modern deep learning techniques. Therefore, there is an increasing need for tools that allow to label large amounts of data as intuitively as possible. In this paper, we introduce SALT, a tool to semi-automatically annotate RGB-D video sequences to generate 3D bounding boxes for full six Degrees of Freedom (DoF) object poses, as well as pixel-level instance segmentation masks for both RGB and depth. Besides bounding box propagation through various interpolation techniques, as well as algorithmically guided instance segmentation, our pipeline also provides built-in pre-processing functionalities to facilitate the data set creation process. By making full use of SALT, annotation time can be reduced by a factor of up to 33.95 for bounding box creation and 8.55 for RGB segmentation without compromising the quality of the automatically generated ground truth.

cs.CV↗

arXiv2021

A Survey on Synchronous Augmented, Virtual and Mixed Reality Remote Collaboration Systems

Remote collaboration systems have become increasingly important in today's society, especially during times where physical distancing is advised. Industry, research and individuals face the challenging task of collaborating and networking over long distances. While video and teleconferencing are already widespread, collaboration systems in augmented, virtual, and mixed reality are still a niche technology. We provide an overview of recent developments of synchronous remote collaboration systems and create a taxonomy by dividing them into three main components that form such systems: Environment, Avatars, and Interaction. A thorough overview of existing systems is given, categorising their main contributions in order to help researchers working in different fields by providing concise information about specific topics such as avatars, virtual environment, visualisation styles and interaction. The focus of this work is clearly on synchronised collaboration from a distance. A total of 82 unique systems for remote collaboration are discussed, including more than 100 publications and 25 commercial systems.

cs.HC↗

arXiv2020

MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene Flow

Contrary to the ongoing trend in automotive applications towards usage of more diverse and more sensors, this work tries to solve the complex scene flow problem under a monocular camera setup, i.e. using a single sensor. Towards this end, we exploit the latest achievements in single image depth estimation, optical flow, and sparse-to-dense interpolation and propose a monocular combination approach (MonoComb) to compute dense scene flow. MonoComb uses optical flow to relate reconstructed 3D positions over time and interpolates occluded areas. This way, existing monocular methods are outperformed in dynamic foreground regions which leads to the second best result among the competitors on the challenging KITTI 2015 scene flow benchmark.

cs.CV↗

arXiv2020

Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function

Images recorded during the lifetime of computer vision based systems undergo a wide range of illumination and environmental conditions affecting the reliability of previously trained machine learning models. Image normalization is hence a valuable preprocessing component to enhance the models' robustness. To this end, we introduce a new strategy for the cost function formulation of encoder-decoder networks to average out all the unimportant information in the input images (e.g. environmental features and illumination changes) to focus on the reconstruction of the salient features (e.g. class instances). Our method exploits the availability of identical sceneries under different illumination and environmental conditions for which we formulate a partially impossible reconstruction target: the input image will not convey enough information to reconstruct the target in its entirety. Its applicability is assessed on three publicly available datasets. We combine the triplet loss as a regularizer in the latent space representation and a nearest neighbour search to improve the generalization to unseen illuminations and class instances. The importance of the aforementioned post-processing is highlighted on an automotive application. To this end, we release a synthetic dataset of sceneries from three different passenger compartments where each scenery is rendered under ten different illumination and environmental conditions: see https://sviro.kl.dfki.de

cs.CV↗

arXiv2020

SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment

This paper demonstrates a system capable of combining a sparse, indirect, monocular visual SLAM, with both offline and real-time Multi-View Stereo (MVS) reconstruction algorithms. This combination overcomes many obstacles encountered by autonomous vehicles or robots employed in agricultural environments, such as overly repetitive patterns, need for very detailed reconstructions, and abrupt movements caused by uneven roads. Furthermore, the use of a monocular SLAM makes our system much easier to integrate with an existing device, as we do not rely on a LiDAR (which is expensive and power consuming), or stereo camera (whose calibration is sensitive to external perturbation e.g. camera being displaced). To the best of our knowledge, this paper presents the first evaluation results for monocular SLAM, and our work further explores unsupervised depth estimation on this specific application scenario by simulating RGB-D SLAM to tackle the scale ambiguity, and shows our approach produces reconstructions that are helpful to various agricultural tasks. Moreover, we highlight that our experiments provide meaningful insight to improve monocular SLAM systems under agricultural settings.

cs.CV↗

arXiv2020

SSGP: Sparse Spatial Guided Propagation for Robust and Generic Interpolation

Interpolation of sparse pixel information towards a dense target resolution finds its application across multiple disciplines in computer vision. State-of-the-art interpolation of motion fields applies model-based interpolation that makes use of edge information extracted from the target image. For depth completion, data-driven learning approaches are widespread. Our work is inspired by latest trends in depth completion that tackle the problem of dense guidance for sparse information. We extend these ideas and create a generic cross-domain architecture that can be applied for a multitude of interpolation problems like optical flow, scene flow, or depth completion. In our experiments, we show that our proposed concept of Sparse Spatial Guided Propagation (SSGP) achieves improvements to robustness, accuracy, or speed compared to specialized algorithms.

cs.CV↗

arXiv2020

A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions

Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to the large (ego-) motion of objects. Our work proposes a novel data-driven approach for temporal fusion of scene flow estimates in a multi-frame setup to overcome the issue of occlusion. Contrary to most previous methods, we do not rely on a constant motion model, but instead learn a generic temporal relation of motion from data. In a second step, a neural network combines bi-directional scene flow estimates from a common reference frame, yielding a refined estimate and a natural byproduct of occlusion masks. This way, our approach provides a fast multi-frame extension for a variety of scene flow estimators, which outperforms the underlying dual-frame approaches.

cs.CV↗

arXiv2020

HPERL: 3D Human Pose Estimation from RGB and LiDAR

In-the-wild human pose estimation has a huge potential for various fields, ranging from animation and action recognition to intention recognition and prediction for autonomous driving. The current state-of-the-art is focused only on RGB and RGB-D approaches for predicting the 3D human pose. However, not using precise LiDAR depth information limits the performance and leads to very inaccurate absolute pose estimation. With LiDAR sensors becoming more affordable and common on robots and autonomous vehicle setups, we propose an end-to-end architecture using RGB and LiDAR to predict the absolute 3D human pose with unprecedented precision. Additionally, we introduce a weakly-supervised approach to generate 3D predictions using 2D pose annotations from PedX [1]. This allows for many new opportunities in the field of 3D human pose estimation.

cs.CV↗

arXiv2020

Generative View Synthesis: From Single-view Semantics to Novel-view Images

Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by converting a semantic map into a photorealistic image. We propose to push the envelope further, and introduce Generative View Synthesis (GVS), which can synthesize multiple photorealistic views of a scene given a single semantic map. We show that the sequential application of existing techniques, e.g., semantics-to-image translation followed by monocular view synthesis, fail at capturing the scene's structure. In contrast, we solve the semantics-to-image translation in concert with the estimation of the 3D layout of the scene, thus producing geometrically consistent novel views that preserve semantic structures. We first lift the input 2D semantic map onto a 3D layered representation of the scene in feature space, thereby preserving the semantic labels of 3D geometric structures. We then project the layered features onto the target views to generate the final novel-view images. We verify the strengths of our method and compare it with several advanced baselines on three different datasets. Our approach also allows for style manipulation and image editing operations, such as the addition or removal of objects, with simple manipulations of the input style images and semantic maps respectively. Visit the project page at https://gvsnet.github.io.

cs.CV↗

arXiv2020

A survey on applications of augmented, mixed and virtual reality for nature and environment

Augmented reality (AR), virtual reality (VR) and mixed reality (MR) are technologies of great potential due to the engaging and enriching experiences they are capable of providing. Their use is rapidly increasing in diverse fields such as medicine, manufacturing or entertainment. However, the possibilities that AR, VR and MR offer in the area of environmental applications are not yet widely explored. In this paper we present the outcome of a survey meant to discover and classify existing AR/VR/MR applications that can benefit the environment or increase awareness on environmental issues. We performed an exhaustive search over several online publication access platforms and past proceedings of major conferences in the fields of AR/VR/MR. Identified relevant papers were filtered based on novelty, technical soundness, impact and topic relevance, and classified into different categories. Referring to the selected papers, we discuss how the applications of each category are contributing to environmental protection, preservation and sensitization purposes. We further analyse these approaches as well as possible future directions in the scope of existing and upcoming AR/VR/MR enabling technologies.

cs.HC↗