arXiv subjects

Vincent Lepetit

Publications and source records attributed to Vincent Lepetit.

At least 109 records · Page 6Linked to original sources

arXiv2017

ALCN: Meta-Learning for Contrast Normalization Applied to Robust 3D Pose Estimation

To be robust to illumination changes when detecting objects in images, 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 very cumbersome, or sometimes even impossible, for some applications such as 3D pose estimation of specific objects, which is the application we focus on in this paper. We therefore propose a novel illumination normalization method that lets us learn to detect objects and estimate their 3D pose under challenging illumination conditions from very few training samples. Our key insight is that normalization parameters should adapt to the input image. In particular, we realized this via a Convolutional Neural Network trained to predict the parameters of a generalization of the Difference-of-Gaussians method. We show that our method significantly outperforms standard normalization methods and demonstrate it on two challenging 3D detection and pose estimation problems.

cs.CV↗

arXiv2017

DeepPrior++: Improving Fast and Accurate 3D Hand Pose Estimation

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 .

cs.CV↗

arXiv2017

Monocular LSD-SLAM Integration within AR System

In this paper, we cover the process of integrating Large-Scale Direct Simultaneous Localization and Mapping (LSD-SLAM) algorithm into our existing AR stereo engine, developed for our modified "Augmented Reality Oculus Rift". With that, we are able to track one of our realworld cameras which are mounted on the rift, within a complete unknown environment. This makes it possible to achieve a constant and full augmentation, synchronizing our 3D movement (x, y, z) in both worlds, the real world and the virtual world. The development for the basic AR setup using the Oculus Rift DK1 and two fisheye cameras is fully documented in our previous paper. After an introduction to image-based registration, we detail the LSD-SLAM algorithm and document our code implementing our integration. The AR stereo engine with Oculus Rift support can be accessed via the GIT repository https://github.com/MaXvanHeLL/ARift.git and the modified LSD-SLAM project used for the integration is available here https://github.com/MaXvanHeLL/LSD-SLAM.git.

cs.CV↗

arXiv2016

Hands Deep in Deep Learning for Hand Pose Estimation

We introduce and evaluate several architectures for Convolutional Neural Networks to predict the 3D joint locations of a hand given a depth map. We first show that a prior on the 3D pose can be easily introduced and significantly improves the accuracy and reliability of the predictions. We also show how to use context efficiently to deal with ambiguities between fingers. These two contributions allow us to significantly outperform the state-of-the-art on several challenging benchmarks, both in terms of accuracy and computation times.

cs.CV↗

arXiv2016

Efficiently Creating 3D Training Data for Fine Hand Pose Estimation

While many recent hand pose estimation methods critically rely on a training set of labelled frames, the creation of such a dataset is a challenging task that has been overlooked so far. As a result, existing datasets are limited to a few sequences and individuals, with limited accuracy, and this prevents these methods from delivering their full potential. We propose a semi-automated method for efficiently and accurately labeling each frame of a hand depth video with the corresponding 3D locations of the joints: The user is asked to provide only an estimate of the 2D reprojections of the visible joints in some reference frames, which are automatically selected to minimize the labeling work by efficiently optimizing a sub-modular loss function. We then exploit spatial, temporal, and appearance constraints to retrieve the full 3D poses of the hand over the complete sequence. We show that this data can be used to train a recent state-of-the-art hand pose estimation method, leading to increased accuracy. The code and dataset can be found on our website https://cvarlab.icg.tugraz.at/projects/hand_detection/

cs.CV↗

arXiv2016

Training a Feedback Loop for Hand Pose Estimation

We propose an entirely data-driven approach to estimating the 3D pose of a hand 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. They remove the need for fitting a 3D model to the input data, which requires both a carefully designed fitting function and algorithm. We show that our approach outperforms state-of-the-art methods, and is efficient as our implementation runs at over 400 fps on a single GPU.

cs.CV↗

arXiv2016

Direct Prediction of 3D Body Poses from Motion Compensated Sequences

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Previous approaches typically compute candidate poses in individual frames and then link them in a post-processing step to resolve ambiguities. By contrast, we directly regress from a spatio-temporal volume of bounding boxes to a 3D pose in the central frame. We further show that, for this approach to achieve its full potential, it is essential to compensate for the motion in consecutive frames so that the subject remains centered. This then allows us to effectively overcome ambiguities and improve upon the state-of-the-art by a large margin on the Human3.6m, HumanEva, and KTH Multiview Football 3D human pose estimation benchmarks.

cs.CV↗

arXiv2016

Fine Hand Segmentation using Convolutional Neural Networks

We propose a method for extracting very accurate masks of hands in egocentric views. Our method is based on a novel Deep Learning architecture: In contrast with current Deep Learning methods, we do not use upscaling layers applied to a low-dimensional representation of the input image. Instead, we extract features with convolutional layers and map them directly to a segmentation mask with a fully connected layer. We show that this approach, when applied in a multi-scale fashion, is both accurate and efficient enough for real-time. We demonstrate it on a new dataset made of images captured in various environments, from the outdoors to offices.

cs.CV↗

arXiv2016

LIFT: Learned Invariant Feature Transform

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-to-end differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

cs.CV↗

arXiv2016

Hashmod: A Hashing Method for Scalable 3D Object Detection

We present a scalable method for detecting objects and estimating their 3D poses in RGB-D data. To this end, we rely on an efficient representation of object views and employ hashing techniques to match these views against the input frame in a scalable way. While a similar approach already exists for 2D detection, we show how to extend it to estimate the 3D pose of the detected objects. In particular, we explore different hashing strategies and identify the one which is more suitable to our problem. We show empirically that the complexity of our method is sublinear with the number of objects and we enable detection and pose estimation of many 3D objects with high accuracy while outperforming the state-of-the-art in terms of runtime.

cs.CV↗

arXiv2016

Structured Prediction of 3D Human Pose with Deep Neural Networks

Most recent approaches to monocular 3D pose estimation rely on Deep Learning. They either train a Convolutional Neural Network to directly regress from image to 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 that relies on an overcomplete auto-encoder to learn a high-dimensional latent pose representation and account for joint dependencies. We demonstrate that our approach outperforms state-of-the-art ones both in terms of structure preservation and prediction accuracy.

cs.CV↗

arXiv2016

Augmented Reality Oculus Rift

This paper covers the whole process of developing an Augmented Reality Stereoscopig Render Engine for the Oculus Rift. To capture the real world in form of a camera stream, two cameras with fish-eye lenses had to be installed on the Oculus Rift DK1 hardware. The idea was inspired by Steptoe \cite{steptoe2014presence}. After the introduction, a theoretical part covers all the most neccessary elements to achieve an AR System for the Oculus Rift, following the implementation part where the code from the AR Stereo Engine is explained in more detail. A short conclusion section shows some results, reflects some experiences and in the final chapter some future works will be discussed. The project can be accessed via the git repository https://github.com/MaXvanHeLL/ARift.git.

cs.GR↗

arXiv2016

Learning to Assign Orientations to Feature Points

We show how to train a Convolutional Neural Network to assign a canonical orientation to feature points given an image patch centered on the feature point. Our method improves feature point matching upon the state-of-the art and can be used in conjunction with any existing rotation sensitive descriptors. To avoid the tedious and almost impossible task of finding a target orientation to learn, we propose to use Siamese networks which implicitly find the optimal orientations during training. We also propose a new type of activation function for Neural Networks that generalizes the popular ReLU, maxout, and PReLU activation functions. This novel activation performs better for our task. We validate the effectiveness of our method extensively with four existing datasets, including two non-planar datasets, as well as our own dataset. We show that we outperform the state-of-the-art without the need of retraining for each dataset.

cs.CV↗

arXiv2015

Predicting People's 3D Poses from Short Sequences

We propose an efficient approach to exploiting motion information from consecutive frames of a video sequence to recover the 3D pose of people. Instead of computing candidate poses in individual frames and then linking them, as is often done, we regress directly from a spatio-temporal block of frames to a 3D pose in the central one. We will demonstrate that this approach allows us to effectively overcome ambiguities and to improve upon the state-of-the-art on challenging sequences.

cs.CV↗

arXiv2015

Learning Descriptors for Object Recognition and 3D Pose Estimation

Detecting poorly textured objects and estimating their 3D pose reliably is still a very challenging problem. We introduce a simple but powerful approach to computing descriptors for object views that efficiently capture both the object identity and 3D pose. By contrast with previous manifold-based approaches, we can rely on the Euclidean distance to evaluate the similarity between descriptors, and therefore use scalable Nearest Neighbor search methods to efficiently handle a large number of objects under a large range of poses. To achieve this, we train a Convolutional Neural Network to compute these descriptors by enforcing simple similarity and dissimilarity constraints between the descriptors. We show that our constraints nicely untangle the images from different objects and different views into clusters that are not only well-separated but also structured as the corresponding sets of poses: The Euclidean distance between descriptors is large when the descriptors are from different objects, and directly related to the distance between the poses when the descriptors are from the same object. These important properties allow us to outperform state-of-the-art object views representations on challenging RGB and RGB-D data.

cs.CV↗

arXiv2015

Global 6DOF Pose Estimation from Untextured 2D City Models

We propose a method for estimating the 3D pose for the camera of a mobile device in outdoor conditions, using only an untextured 2D model. Previous methods compute only a relative pose using a SLAM algorithm, or require many registered images, which are cumbersome to acquire. By contrast, our method returns an accurate, absolute camera pose in an absolute referential using simple 2D+height maps, which are broadly available, to refine a first estimate of the pose provided by the device's sensors. We show how to first estimate the camera absolute orientation from straight line segments, and then how to estimate the translation by aligning the 2D map with a semantic segmentation of the input image. We demonstrate the robustness and accuracy of our approach on a challenging dataset.

cs.CV↗

arXiv2015

TILDE: A Temporally Invariant Learned DEtector

We introduce a learning-based approach to detect repeatable keypoints under drastic imaging changes of weather and lighting conditions to which state-of-the-art keypoint detectors are surprisingly sensitive. We first identify good keypoint candidates in multiple training images taken from the same viewpoint. We then train a regressor to predict a score map whose maxima are those points so that they can be found by simple non-maximum suppression. As there are no standard datasets to test the influence of these kinds of changes, we created our own, which we will make publicly available. We will show that our method significantly outperforms the state-of-the-art methods in such challenging conditions, while still achieving state-of-the-art performance on the untrained standard Oxford dataset.

cs.CV↗

arXiv2014

On Rendering Synthetic Images for Training an Object Detector

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a coarse 3D model of the target object. These parameters can then be reused to generate an unlimited number of training images of the object of interest in arbitrary 3D poses, which can then be used to increase classification performances. A key insight of our approach is that the synthetically generated images should be similar to real images, not in terms of image quality, but rather in terms of features used during the detector training. We show in the context of drone, plane, and car detection that using such synthetically generated images yields significantly better performances than simply perturbing real images or even synthesizing images in such way that they look very realistic, as is often done when only limited amounts of training data are available.

cs.CV↗