arXiv subjects

Francesc Moreno-Noguer

Publications and source records attributed to Francesc Moreno-Noguer.

At least 73 records · Page 4Linked to original sources

arXiv2019

Human Motion Prediction via Spatio-Temporal Inpainting

We propose a Generative Adversarial Network (GAN) to forecast 3D human motion given a sequence of past 3D skeleton poses. While recent GANs have shown promising results, they can only forecast plausible motion over relatively short periods of time (few hundred milliseconds) and typically ignore the absolute position of the skeleton w.r.t. the camera. Our scheme provides long term predictions (two seconds or more) for both the body pose and its absolute position. Our approach builds upon three main contributions. First, we represent the data using a spatio-temporal tensor of 3D skeleton coordinates which allows formulating the prediction problem as an inpainting one, for which GANs work particularly well. Secondly, we design an architecture to learn the joint distribution of body poses and global motion, capable to hypothesize large chunks of the input 3D tensor with missing data. And finally, we argue that the L2 metric, considered so far by most approaches, fails to capture the actual distribution of long-term human motion. We propose two alternative metrics, based on the distribution of frequencies, that are able to capture more realistic motion patterns. Extensive experiments demonstrate our approach to significantly improve the state of the art, while also handling situations in which past observations are corrupted by occlusions, noise and missing frames.

cs.CV↗

arXiv2019

Improving Map Re-localization with Deep 'Movable' Objects Segmentation on 3D LiDAR Point Clouds

Localization and Mapping is an essential component to enable Autonomous Vehicles navigation, and requires an accuracy exceeding that of commercial GPS-based systems. Current odometry and mapping algorithms are able to provide this accurate information. However, the lack of robustness of these algorithms against dynamic obstacles and environmental changes, even for short time periods, forces the generation of new maps on every session without taking advantage of previously obtained ones. In this paper we propose the use of a deep learning architecture to segment movable objects from 3D LiDAR point clouds in order to obtain longer-lasting 3D maps. This will in turn allow for better, faster and more accurate re-localization and trajectoy estimation on subsequent days. We show the effectiveness of our approach in a very dynamic and cluttered scenario, a supermarket parking lot. For that, we record several sequences on different days and compare localization errors with and without our movable objects segmentation method. Results show that we are able to accurately re-locate over a filtered map, consistently reducing trajectory errors between an average of 35.1% with respect to a non-filtered map version and of 47.9% with respect to a standalone map created on the current session.

cs.CV↗

arXiv2019

Semantic Relatedness Based Re-ranker for Text Spotting

Applications such as textual entailment, plagiarism detection or document clustering rely on the notion of semantic similarity, and are usually approached with dimension reduction techniques like LDA or with embedding-based neural approaches. We present a scenario where semantic similarity is not enough, and we devise a neural approach to learn semantic relatedness. The scenario is text spotting in the wild, where a text in an image (e.g. street sign, advertisement or bus destination) must be identified and recognized. Our goal is to improve the performance of vision systems by leveraging semantic information. Our rationale is that the text to be spotted is often related to the image context in which it appears (word pairs such as Delta-airplane, or quarters-parking are not similar, but are clearly related). We show how learning a word-to-word or word-to-sentence relatedness score can improve the performance of text spotting systems up to 2.9 points, outperforming other measures in a benchmark dataset.

cs.CL↗

arXiv2019

3DPeople: Modeling the Geometry of Dressed Humans

Recent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothing geometry. In this paper, we present an approach to model dressed humans and predict their geometry from single images. We contribute in three fundamental aspects of the problem, namely, a new dataset, a novel shape parameterization algorithm and an end-to-end deep generative network for predicting shape. First, we present 3DPeople, a large-scale synthetic dataset with 2.5 Million photo-realistic images of 80 subjects performing 70 activities and wearing diverse outfits. Besides providing textured 3D meshes for clothes and body, we annotate the dataset with segmentation masks, skeletons, depth, normal maps and optical flow. All this together makes 3DPeople suitable for a plethora of tasks. We then represent the 3D shapes using 2D geometry images. To build these images we propose a novel spherical area-preserving parameterization algorithm based on the optimal mass transportation method. We show this approach to improve existing spherical maps which tend to shrink the elongated parts of the full body models such as the arms and legs, making the geometry images incomplete. Finally, we design a multi-resolution deep generative network that, given an input image of a dressed human, predicts his/her geometry image (and thus the clothed body shape) in an end-to-end manner. We obtain very promising results in jointly capturing body pose and clothing shape, both for synthetic validation and on the wild images.

cs.CV↗

arXiv2019

Fast video object segmentation with Spatio-Temporal GANs

Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference mask at the first frame (aided sometimes by optical flow or the previous mask). These models, however, are prone to fail under rapid appearance changes or occlusions due to their limitations in modelling the temporal component. On the other hand, very recently, other approaches learned long-term features using a convolutional LSTM to leverage the information from all previous video frames. Even though these models achieve better temporal representations, they still have to be fine-tuned for every new video sequence. In this paper, we present an intermediate solution and devise a novel GAN architecture, FaSTGAN, to learn spatio-temporal object models over finite temporal windows. To achieve this, we concentrate all the heavy computational load to the training phase with two critics that enforce spatial and temporal mask consistency over the last K frames. Then at test time, we only use a relatively light regressor, which reduces the inference time considerably. As a result, our approach combines a high resiliency to sudden geometric and photometric object changes with efficiency at test time (no need for fine-tuning nor post-processing). We demonstrate that the accuracy of our method is on par with state-of-the-art techniques on the challenging YouTube-VOS and DAVIS datasets, while running at 32 fps, about 4x faster than the closest competitor.

cs.CV↗

arXiv2018

Visual Re-ranking with Natural Language Understanding for Text Spotting

Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from natural language processing perspective to fill the gap between language and vision. We propose a post-processing approach to improve scene text recognition accuracy by using occurrence probabilities of words (unigram language model), and the semantic correlation between scene and text. For this, we initially rely on an off-the-shelf deep neural network, already trained with a large amount of data, which provides a series of text hypotheses per input image. These hypotheses are then re-ranked using word frequencies and semantic relatedness with objects or scenes in the image. As a result of this combination, the performance of the original network is boosted with almost no additional cost. We validate our approach on ICDAR'17 dataset.

cs.CV↗

arXiv2018

Visual Semantic Re-ranker for Text Spotting

Many current state-of-the-art methods for text recognition are based on purely local information and ignore the semantic correlation between text and its surrounding visual context. In this paper, we propose a post-processing approach to improve the accuracy of text spotting by using the semantic relation between the text and the scene. We initially rely on an off-the-shelf deep neural network that provides a series of text hypotheses for each input image. These text hypotheses are then re-ranked using the semantic relatedness with the object in the image. As a result of this combination, the performance of the original network is boosted with a very low computational cost. The proposed framework can be used as a drop-in complement for any text-spotting algorithm that outputs a ranking of word hypotheses. We validate our approach on ICDAR'17 shared task dataset.

cs.CV↗

arXiv2018

Unsupervised Person Image Synthesis in Arbitrary Poses

We present a novel approach for synthesizing photo-realistic images of people in arbitrary poses using generative adversarial learning. Given an input image of a person and a desired pose represented by a 2D skeleton, our model renders the image of the same person under the new pose, synthesizing novel views of the parts visible in the input image and hallucinating those that are not seen. This problem has recently been addressed in a supervised manner, i.e., during training the ground truth images under the new poses are given to the network. We go beyond these approaches by proposing a fully unsupervised strategy. We tackle this challenging scenario by splitting the problem into two principal subtasks. First, we consider a pose conditioned bidirectional generator that maps back the initially rendered image to the original pose, hence being directly comparable to the input image without the need to resort to any training image. Second, we devise a novel loss function that incorporates content and style terms, and aims at producing images of high perceptual quality. Extensive experiments conducted on the DeepFashion dataset demonstrate that the images rendered by our model are very close in appearance to those obtained by fully supervised approaches.

cs.CV↗

arXiv2018

Geometry-Aware Network for Non-Rigid Shape Prediction from a Single View

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.

cs.CV↗

arXiv2018

Deep Lidar CNN to Understand the Dynamics of Moving Vehicles

Perception technologies in Autonomous Driving are experiencing their golden age due to the advances in Deep Learning. Yet, most of these systems rely on the semantically rich information of RGB images. Deep Learning solutions applied to the data of other sensors typically mounted on autonomous cars (e.g. lidars or radars) are not explored much. In this paper we propose a novel solution to understand the dynamics of moving vehicles of the scene from only lidar information. The main challenge of this problem stems from the fact that we need to disambiguate the proprio-motion of the 'observer' vehicle from that of the external 'observed' vehicles. For this purpose, we devise a CNN architecture which at testing time is fed with pairs of consecutive lidar scans. However, in order to properly learn the parameters of this network, during training we introduce a series of so-called pretext tasks which also leverage on image data. These tasks include semantic information about vehicleness and a novel lidar-flow feature which combines standard image-based optical flow with lidar scans. We obtain very promising results and show that including distilled image information only during training, allows improving the inference results of the network at test time, even when image data is no longer used.

cs.CV↗

arXiv2018

Hallucinating Dense Optical Flow from Sparse Lidar for Autonomous Vehicles

In this paper we propose a novel approach to estimate dense optical flow from sparse lidar data acquired on an autonomous vehicle. This is intended to be used as a drop-in replacement of any image-based optical flow system when images are not reliable due to e.g. adverse weather conditions or at night. In order to infer high resolution 2D flows from discrete range data we devise a three-block architecture of multiscale filters that combines multiple intermediate objectives, both in the lidar and image domain. To train this network we introduce a dataset with approximately 20K lidar samples of the Kitti dataset which we have augmented with a pseudo ground-truth image-based optical flow computed using FlowNet2. We demonstrate the effectiveness of our approach on Kitti, and show that despite using the low-resolution and sparse measurements of the lidar, we can regress dense optical flow maps which are at par with those estimated with image-based methods.

cs.CV↗

arXiv2018

GANimation: Anatomically-aware Facial Animation from a Single Image

Recent advances in Generative Adversarial Networks (GANs) have shown impressive results for task of facial expression synthesis. The most successful architecture is StarGAN, that conditions GANs generation process with images of a specific domain, namely a set of images of persons sharing the same expression. While effective, this approach can only generate a discrete number of expressions, determined by the content of the dataset. To address this limitation, in this paper, we introduce a novel GAN conditioning scheme based on Action Units (AU) annotations, which describes in a continuous manifold the anatomical facial movements defining a human expression. Our approach allows controlling the magnitude of activation of each AU and combine several of them. Additionally, we propose a fully unsupervised strategy to train the model, that only requires images annotated with their activated AUs, and exploit attention mechanisms that make our network robust to changing backgrounds and lighting conditions. Extensive evaluation show that our approach goes beyond competing conditional generators both in the capability to synthesize a much wider range of expressions ruled by anatomically feasible muscle movements, as in the capacity of dealing with images in the wild.

cs.CV↗

arXiv2018

Deconvolutional Networks for Point-Cloud Vehicle Detection and Tracking in Driving Scenarios

Vehicle detection and tracking is a core ingredient for developing autonomous driving applications in urban scenarios. Recent image-based Deep Learning (DL) techniques are obtaining breakthrough results in these perceptive tasks. However, DL research has not yet advanced much towards processing 3D point clouds from lidar range-finders. These sensors are very common in autonomous vehicles since, despite not providing as semantically rich information as images, their performance is more robust under harsh weather conditions than vision sensors. In this paper we present a full vehicle detection and tracking system that works with 3D lidar information only. Our detection step uses a Convolutional Neural Network (CNN) that receives as input a featured representation of the 3D information provided by a Velodyne HDL-64 sensor and returns a per-point classification of whether it belongs to a vehicle or not. The classified point cloud is then geometrically processed to generate observations for a multi-object tracking system implemented via a number of Multi-Hypothesis Extended Kalman Filters (MH-EKF) that estimate the position and velocity of the surrounding vehicles. The system is thoroughly evaluated on the KITTI tracking dataset, and we show the performance boost provided by our CNN-based vehicle detector over a standard geometric approach. Our lidar-based approach uses about a 4% of the data needed for an image-based detector with similarly competitive results.

cs.CV↗

arXiv2018

Joint Coarse-And-Fine Reasoning for Deep Optical Flow

We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.

cs.CV↗

arXiv2016

3D Human Pose Estimation from a Single Image via Distance Matrix Regression

This paper addresses the problem of 3D human pose estimation from a single image. We follow a standard two-step pipeline by first detecting the 2D position of the $N$ body joints, and then using these observations to infer 3D pose. For the first step, we use a recent CNN-based detector. For the second step, most existing approaches perform 2$N$-to-3$N$ regression of the Cartesian joint coordinates. We show that more precise pose estimates can be obtained by representing both the 2D and 3D human poses using $N\times N$ distance matrices, and formulating the problem as a 2D-to-3D distance matrix regression. For learning such a regressor we leverage on simple Neural Network architectures, which by construction, enforce positivity and symmetry of the predicted matrices. The approach has also the advantage to naturally handle missing observations and allowing to hypothesize the position of non-observed joints. Quantitative results on Humaneva and Human3.6M datasets demonstrate consistent performance gains over state-of-the-art. Qualitative evaluation on the images in-the-wild of the LSP dataset, using the regressor learned on Human3.6M, reveals very promising generalization results.

cs.CV↗

arXiv2016

BreakingNews: Article Annotation by Image and Text Processing

Building upon recent Deep Neural Network architectures, current approaches lying in the intersection of computer vision and natural language processing have achieved unprecedented breakthroughs in tasks like automatic captioning or image retrieval. Most of these learning methods, though, rely on large training sets of images associated with human annotations that specifically describe the visual content. In this paper we propose to go a step further and explore the more complex cases where textual descriptions are loosely related to the images. We focus on the particular domain of News articles in which the textual content often expresses connotative and ambiguous relations that are only suggested but not directly inferred from images. We introduce new deep learning methods that address source detection, popularity prediction, article illustration and geolocation of articles. An adaptive CNN architecture is proposed, that shares most of the structure for all the tasks, and is suitable for multitask and transfer learning. Deep Canonical Correlation Analysis is deployed for article illustration, and a new loss function based on Great Circle Distance is proposed for geolocation. Furthermore, we present BreakingNews, a novel dataset with approximately 100K news articles including images, text and captions, and enriched with heterogeneous meta-data (such as GPS coordinates and popularity metrics). We show this dataset to be appropriate to explore all aforementioned problems, for which we provide a baseline performance using various Deep Learning architectures, and different representations of the textual and visual features. We report very promising results and bring to light several limitations of current state-of-the-art in this kind of domain, which we hope will help spur progress in the field.

cs.CV↗

arXiv2016

TED: A Tolerant Edit Distance for Segmentation Evaluation

In this paper, we present a novel error measure to compare a segmentation against ground truth. This measure, which we call Tolerant Edit Distance (TED), is motivated by two observations: (1) Some errors, like small boundary shifts, are tolerable in practice. Which errors are tolerable is application dependent and should be a parameter of the measure. (2) Non-tolerable errors have to be corrected manually. The time needed to do so should be reflected by the error measure. Using integer linear programming, the TED finds the minimal weighted sum of split and merge errors exceeding a given tolerance criterion, and thus provides a time-to-fix estimate. In contrast to commonly used measures like Rand index or variation of information, the TED (1) does not count small, but tolerable, differences, (2) provides intuitive numbers, (3) gives a time-to-fix estimate, and (4) can localize and classify the type of errors. By supporting both isotropic and anisotropic volumes and having a flexible tolerance criterion, the TED can be adapted to different requirements. On example segmentations for 3D neuron segmentation, we demonstrate that the TED is capable of counting topological errors, while ignoring small boundary shifts.

cs.CV↗

arXiv2015

Structured Prediction with Output Embeddings for Semantic Image Annotation

We address the task of annotating images with semantic tuples. Solving this problem requires an algorithm which is able to deal with hundreds of classes for each argument of the tuple. In such contexts, data sparsity becomes a key challenge, as there will be a large number of classes for which only a few examples are available. We propose handling this by incorporating feature representations of both the inputs (images) and outputs (argument classes) into a factorized log-linear model, and exploiting the flexibility of scoring functions based on bilinear forms. Experiments show that integrating feature representations of the outputs in the structured prediction model leads to better overall predictions. We also conclude that the best output representation is specific for each type of argument.

cs.CV↗