Related papers: Motion Consistency Loss for Monocular Visual Odome…
Monocular visual odometry (VO) is a fundamental computer vision problem with applications in autonomous navigation, augmented reality and more. While deep learning-based methods have recently shown superior accuracy compared to traditional…
This work is based on a questioning of the quality metrics used by deep neural networks performing depth prediction from a single image, and then of the usability of recently published works on unsupervised learning of depth from videos. To…
This paper presents a learned model to predict the robot-centric velocity of an underwater robot through dynamics-aware proprioception. The method exploits a recurrent neural network using as inputs inertial cues, motor commands, and…
Deep learning has recently demonstrated its excellent performance on the task of multi-view stereo (MVS). However, loss functions applied for deep MVS are rarely studied. In this paper, we first analyze existing loss functions' properties…
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics…
Pedestrian dead reckoning is a challenging task due to the low-cost inertial sensor error accumulation. Recent research has shown that deep learning methods can achieve impressive performance in handling this issue. In this letter, we…
Stereo vision generally involves the computation of pixel correspondences and estimation of disparities between rectified image pairs. In many applications, including simultaneous localization and mapping (SLAM) and 3D object detection, the…
Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a…
Existing losses used in deep metric learning (DML) for image retrieval often lead to highly non-uniform intra-class and inter-class representation structures across test classes and data distributions. When combined with the common practice…
Recent learning-based LiDAR odometry methods have demonstrated their competitiveness. However, most methods still face two substantial challenges: 1) the 2D projection representation of LiDAR data cannot effectively encode 3D structures…
Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…
We propose D3VO as a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network…
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our technical contributions are three-fold. First, we…
Visual odometry (VO) is a prevalent way to deal with the relative localization problem, which is becoming increasingly mature and accurate, but it tends to be fragile under challenging environments. Comparing with classical geometry-based…
Video depth estimation is crucial in various applications, such as scene reconstruction and augmented reality. In contrast to the naive method of estimating depths from images, a more sophisticated approach uses temporal information,…
Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video.…
Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…
Perceiving the physical world in 3D is fundamental for self-driving applications. Although temporal motion is an invaluable resource to human vision for detection, tracking, and depth perception, such features have not been thoroughly…
In this paper, we propose a novel trajectory learning method that exploits motion trajectories on topological map using recurrent neural network for temporally consistent geolocalization of object. Inspired by human's ability to both be…
Significant attention has been attracted to deep learning-based depth estimates. Dynamic objects become the most hard problems in inter-frame-supervised depth estimates due to the uncertainty in adjacent frames. Thus, integrating optical…