Search

The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots. It allows them to plan early and decide accordingly. Motivated by this observation, in this paper we utilize information from a video sequence with a narrow field-of-view to infer the scene at a wider field-of-view. To this end, we propose a temporally consistent field-of-view extrapolation framework, namely FoV-Net, that: (1) leverages 3D information to propagate the observed scene parts from past frames; (2) aggregates the propagated multi-frame information using an attention-based feature aggregation module and a gated self-attention module, simultaneously hallucinating any unobserved scene parts; and (3) assigns an interpretable uncertainty value at each pixel. Extensive experiments show that FoV-Net does not only extrapolate the temporally consistent wide field-of-view scene better than existing alternatives, but also provides the associated uncertainty which may benefit critical decision-making downstream applications. Project page is at http://charliememory.github.io/RAL21_FoV., Accepted to IEEE Robotics and Automation Letters and ICRA2021. Project page http://charliememory.github.io/RAL21_FoV

State-of-the-art frame interpolation methods generate intermediate frames by inferring object motions in the image from consecutive key-frames. In the absence of additional information, first-order approximations, i.e. optical flow, must be used, but this choice restricts the types of motions that can be modeled, leading to errors in highly dynamic scenarios. Event cameras are novel sensors that address this limitation by providing auxiliary visual information in the blind-time between frames. They asynchronously measure per-pixel brightness changes and do this with high temporal resolution and low latency. Event-based frame interpolation methods typically adopt a synthesis-based approach, where predicted frame residuals are directly applied to the key-frames. However, while these approaches can capture non-linear motions they suffer from ghosting and perform poorly in low-texture regions with few events. Thus, synthesis-based and flow-based approaches are complementary. In this work, we introduce Time Lens, a novel method that leverages the advantages of both. We extensively evaluate our method on three synthetic and two real benchmarks where we show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods. Finally, we release a new large-scale dataset in highly dynamic scenarios, aimed at pushing the limits of existing methods.

With the advent of deep learning, many dense prediction tasks, i.e. tasks that produce pixel-level predictions, have seen significant performance improvements. The typical approach is to learn these tasks in isolation, that is, a separate neural network is trained for each individual task. Yet, recent multi-task learning (MTL) techniques have shown promising results w.r.t. performance, computations and/or memory footprint, by jointly tackling multiple tasks through a learned shared representation. In this survey, we provide a well-rounded view on state-of-the-art deep learning approaches for MTL in computer vision, explicitly emphasizing on dense prediction tasks. Our contributions concern the following. First, we consider MTL from a network architecture point-of-view. We include an extensive overview and discuss the advantages/disadvantages of recent popular MTL models. Second, we examine various optimization methods to tackle the joint learning of multiple tasks. We summarize the qualitative elements of these works and explore their commonalities and differences. Finally, we provide an extensive experimental evaluation across a variety of dense prediction benchmarks to examine the pros and cons of the different methods, including both architectural and optimization based strategies., Accepted to T-PAMI. Code + Suppl. Mat. can be found here: https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch IEEE Copyright Notice

We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a multi-task learning setting, a proper encoding of their relationships can further improve performance on both tasks. Motivated by this observation, we propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. To capture the cross-task relationships, we propose a neural network architecture that contains task-specific and cross-task refinement heads. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain. We experimentally observe improvements in both tasks' performance because the complementary information present in these tasks is better captured. Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance. The implementation is available at https://github.com/susaha/ctrl-uda., 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), ISBN:978-1-6654-4509-2, ISBN:978-1-6654-4510-8

In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at other scales, and vice versa. We propose a novel architecture, namely MTI-Net, that builds upon this finding in three ways. First, it explicitly models task interactions at every scale via a multi-scale multi-modal distillation unit. Second, it propagates distilled task information from lower to higher scales via a feature propagation module. Third, it aggregates the refined task features from all scales via a feature aggregation unit to produce the final per-task predictions.

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. In doing so, we remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by large margins, in particular +26.6% on CIFAR10, +25.0% on CIFAR100-20 and +21.3% on STL10 in terms of classification accuracy. Furthermore, our method is the first to perform well on a large-scale dataset for image classification. In particular, we obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime without the use of any ground-truth annotations. The code is made publicly available at https://github.com/wvangansbeke/Unsupervised-Classification., Comment: Accepted at ECCV 2020. Includes supplementary. Code and pretrained models at https://github.com/wvangansbeke/Unsupervised-Classification

Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks. The state-of-the-art anti-spoofing techniques leverage the ability of deep neural networks to learn discriminative features, based on cues from the training set images or video samples, in an effort to detect spoof attacks. However, due to the particular nature of the problem, i.e. large variability due to factors like different backgrounds, lighting conditions, camera resolutions, spoof materials, etc., these techniques typically fail to generalize to new samples. In this paper, we explicitly tackle this problem and propose a class-conditional domain discriminator module, that, coupled with a gradient reversal layer, tries to generate live and spoof features that are discriminative, but at the same time robust against the aforementioned variability factors. Extensive experimental analysis shows the effectiveness of the proposed method over existing image- and video-based anti-spoofing techniques, both in terms of numerical improvement as well as when visualizing the learned features., Comment: CVPR 2020 Biometrics Workshop

Lecture Notes in Computer Science, 12365, ISSN:0302-9743, ISSN:1611-3349, Computer Vision – ECCV 2020, ISBN:978-3-030-58564-8, ISBN:978-3-030-58565-5

Semantic segmentation approaches can largely be divided into two categories. One with accurate results but slow inference, and another one with real-time inference but sacrificing some performance for speed. In this paper, we try to exploit the benefits of both categories, i.e. accuracy and speed, through the use of model selection techniques. Using the uncertainty, calculated from the entropy map, as our selection criterion, we leverage the speed of the fast, but not so accurate, model for regions with high certainty, that comprise the majority of the input image, while for a few, carefully selected regions with low certainty we employ an accurate, yet expensive, model, to predict the semantic labels. Our experimental results show that our method greatly boosts the performance of the baseline model, while retaining reasonable inference speeds.

In this paper, we present a method that estimates reflectance and illumination information from a single image depicting a single-material specular object from a given class under natural illumination. We follow a data-driven, learning-based approach trained on a very large dataset, but in contrast to earlier work we do not assume one or more components (shape, reflectance, or illumination) to be known. We propose a two-step approach, where we first estimate the object's reflectance map, and then further decompose it into reflectance and illumination. For the first step, we introduce a Convolutional Neural Network (CNN) that directly predicts a reflectance map from the input image itself, as well as an indirect scheme that uses additional supervision, first estimating surface orientation and afterwards inferring the reflectance map using a learning-based sparse data interpolation technique. For the second step, we suggest a CNN architecture to reconstruct both Phong reflectance parameters and high-resolution spherical illumination maps from the reflectance map. We also propose new datasets to train these CNNs. We demonstrate the effectiveness of our approach for both steps by extensive quantitative and qualitative evaluation in both synthetic and real data as well as through numerous applications, that show improvements over the state-of-the-art.

Modern cars are incorporating an increasing number of driver assist features, among which automatic lane keeping. The latter allows the car to properly position itself within the road lanes, which is also crucial for any subsequent lane departure or trajectory planning decision in fully autonomous cars. Traditional lane detection methods rely on a combination of highly-specialized, hand-crafted features and heuristics, usually followed by post-processing techniques, that are computationally expensive and prone to scalability due to road scene variations. More recent approaches leverage deep learning models, trained for pixel-wise lane segmentation, even when no markings are present in the image due to their big receptive field. Despite their advantages, these methods are limited to detecting a pre-defined, fixed number of lanes, e.g. ego-lanes, and can not cope with lane changes. In this paper, we go beyond the aforementioned limitations and propose to cast the lane detection problem as an instance segmentation problem - in which each lane forms its own instance - that can be trained end-to-end. To parametrize the segmented lane instances before fitting the lane, we further propose to apply a learned perspective transformation, conditioned on the image, in contrast to a fixed "bird's-eye view" transformation. By doing so, we ensure a lane fitting which is robust against road plane changes, unlike existing approaches that rely on a fixed, pre-defined transformation. In summary, we propose a fast lane detection algorithm, running at 50 fps, which can handle a variable number of lanes and cope with lane changes. We verify our method on the tuSimple dataset and achieve competitive results.

Pixel-wise semantic image labeling is an important, yet challenging task with many applications. Especially in autonomous driving systems, it allows for a full understanding of the system's surroundings, which is crucial for trajectory planning. Typical approaches to tackle this problem involve either the training of deep networks on vast amounts of images to directly infer the labels or the use of probabilistic graphical models to jointly model the dependencies of the input (i.e. images) and output (i.e. labels). Yet, the former approaches do not capture the structure of the output labels, which is crucial for the performance of dense labeling, and the latter rely on carefully hand-designed priors that require costly parameter tuning via optimization techniques, which in turn leads to long inference times. To alleviate these restrictions, we explore how to arrive at dense semantic pixel labels given both the input image and an initial estimate of the output labels. We propose a parallel architecture that: 1) exploits the context information through a LabelPropagation network to propagate correct labels from nearby pixels to improve the object boundaries, 2) uses a LabelReplacement network to directly replace possibly erroneous, initial labels with new ones, and 3) combines the different intermediate results via a Fusion network to obtain the final per-pixel label. We experimentally validate our approach on two different datasets for semantic segmentation, where we show improvements over the state-of-the-art. We also provide both a quantitative and qualitative analysis of the generated results.

Generating novel, yet realistic, images of persons is a challenging task due to the complex interplay between the different image factors, such as the foreground, background and pose information. In this work, we aim at generating such images based on a novel, two-stage reconstruction pipeline that learns a disentangled representation of the aforementioned image factors and generates novel person images at the same time. First, a multi-branched reconstruction network is proposed to disentangle and encode the three factors into embedding features, which are then combined to re-compose the input image itself. Second, three corresponding mapping functions are learned in an adversarial manner in order to map Gaussian noise to the learned embedding feature space, for each factor respectively. Using the proposed framework, we can manipulate the foreground, background and pose of the input image, and also sample new embedding features to generate such targeted manipulations, that provide more control over the generation process. Experiments on Market-1501 and Deepfashion datasets show that our model does not only generate realistic person images with new foregrounds, backgrounds and poses, but also manipulates the generated factors and interpolates the in-between states. Another set of experiments on Market-1501 shows that our model can also be beneficial for the person re-identification task., Published at CVPR'18 (Spotlight). Corresponding author is Qianru Sun

Research on visual material recognition has traditionally been based on texture analysis. Whereas older work has focused on uncluttered scenes, more recent contributions allowed for material recognition 'in the wild'. Quite some objects have untextured surfaces, however. Especially man-made examples are legion. The most obvious cue to use in such cases would be reflection information. Yet, methods to that effect are lacking. It is clear that more than an estimate of a scalar albedo is needed, and a more complete reflectance model has to be derived. Rather than using an extensive lab setup, we propose a system that only requires the 3D shape of objects and a regular, commercial camera to capture their appearance in a single image, to perform material classification under unknown illumination. To this end, we rely on a Gaussian Process Latent Variable Model (GPLVM) with a discriminative prior to learn a low-dimensional manifold suitable for material classification of reflectance maps, i.e. from a 2D image of a singlematerial sphere under natural illumination. We evaluated our method based on experiments generated from synthetic and real-life data. Although recognizing materials without texture (or object recognition) is not a trivial problem, our method achieves about 75% recognition accuracy, about 27% higher than human performance.

How much does a single image reveal about the environment it was taken in? In this paper, we investigate how much of that information can be retrieved from a foreground object, combined with the background (i.e. the visible part of the environment). Assuming it is not perfectly diffuse, the foreground object acts as a complexly shaped and far-from-perfect mirror. An additional challenge is that its appearance confounds the light coming from the environment with the unknown materials it is made of. We propose a learning-based approach to predict the environment from multiple reflectance maps that are computed from approximate surface normals. The proposed method allows us to jointly model the statistics of environments and material properties. We train our system from synthesized training data, but demonstrate its applicability to real-world data. Interestingly, our analysis shows that the information obtained from objects made out of multiple materials often is complementary and leads to better performance., Comment: Accepted to ICCV. Project: http://homes.esat.kuleuven.be/~sgeorgou/multinatillum/

© 2015 IEEE. The problem of estimating a full BRDF from partial observations has already been studied using either parametric or non-parametric approaches. The goal in each case is to best match this sparse set of input measurements. In this paper we address the problem of inferring higher order reflectance information starting from the minimal input of a single BRDF slice. We begin from the prototypical case of a homogeneous sphere, lit by a head-on light source, which only holds information about less than 0.001% of the whole BRDF domain. We propose a novel method to infer the higher dimensional properties of the material's BRDF, based on the statistical distribution of known material characteristics observed in real-life samples. We evaluated our method based on a large set of experiments generated from real-world BRDFs and newly measured materials. Although inferring higher dimensional BRDFs from such modest training is not a trivial problem, our method performs better than state-of-the-art parametric, semi-parametric and non-parametric approaches. Finally, we discuss interesting applications on material re-lighting, and flash-based photography. Georgoulis S., Vanweddingen V., Proesmans M., Van Gool L., ''A gaussian process latent variable model for BRDF inference'', Proceedings 15th international conference on computer vision - ICCV 2015, pp. 3559-3567, December 11-18, 2015, Santiago, Chile. ispartof: pages:3559-3567 ispartof: Proceedings ICCV 2015 vol:2015 International Conference on Computer Vision, ICCV 2015 pages:3559-3567 ispartof: International conference on computer vision - ICCV 2015 location:Santiago, Chile date:11 Dec - 18 Dec 2015 status: published

In this work, we investigate the use of simple flash-based photography to capture an object's 3D shape and reflectance characteristics at the same time. The presented method is based on the principles of Structure from Motion (SfM) and Photometric Stereo (PS), yet, we make sure not to use more than readily-available consumer equipment, like a camera with flash. Starting from a SfM-generated mesh, we apply PS to refine both geometry and reflectance, where the latter is expressed in terms of data-driven Bidirectional Reflectance Distribution Function (BRDF) representations. We also introduce a novel approach to infer complete BRDFs starting from the sparsely sampled data-driven reflectance information captured with this setup. Our approach is experimentally validated by modeling several challenging objects, both synthetic and real.

An innovative pain management system, namely Epione, is presented here. Epione deals with three main types of pain, i.e., acute pain, chronic pain, and phantom limb pain. In particular, by using facial expression analysis, Epione forms a dynamic pain meter, which then triggers biofeedback and augmented reality-based destruction scenarios, in an effort to maximize patient's pain relief. This unique combination sets Epione not only a novel pain management approach, but also a means that provides an understanding and integration of the needs of the whole community involved i.e., patients and physicians, in a joint attempt to facilitate easing of their suffering, provide efficient monitoring and contribute to a better quality of life.