Related papers: SE3-Pose-Nets: Structured Deep Dynamics Models for…
This paper contributes a novel and modularized learning-based method for aerial robots navigating cluttered environments containing hard-to-perceive thin obstacles without assuming access to a map or the full pose estimation of the robot.…
Depth estimation is a crucial technology in robotics. Recently, self-supervised depth estimation methods have demonstrated great potential as they can efficiently leverage large amounts of unlabelled real-world data. However, most existing…
The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…
Agile flights of autonomous quadrotors in cluttered environments require constrained motion planning and control subject to translational and rotational dynamics. Traditional model-based methods typically demand complicated design and heavy…
Learning a good 3D human pose representation is important for human pose related tasks, e.g. human 3D pose estimation and action recognition. Within all these problems, preserving the intrinsic pose information and adapting to view…
This article presents a novel telepresence system for advancing aerial manipulation in dynamic and unstructured environments. The proposed system not only features a haptic device, but also a virtual reality (VR) interface that provides…
Temporal modeling and spatio-temporal collaboration are pivotal techniques for video-based human pose estimation. Most state-of-the-art methods adopt optical flow or temporal difference, learning local visual content correspondence across…
Fast and accurate upper-body and head pose estimation is a key task for automatic monitoring of driver attention, a challenging context characterized by severe illumination changes, occlusions and extreme poses. In this work, we present a…
Intuitive user interfaces are indispensable to interact with the human centric smart environments. In this paper, we propose a unified framework that recognizes both static and dynamic gestures, using simple RGB vision (without depth…
Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture…
Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a…
Finding an embedding space for a linear approximation of a nonlinear dynamical system enables efficient system identification and control synthesis. The Koopman operator theory lays the foundation for identifying the nonlinear-to-linear…
We present a novel embedding approach for video instance segmentation. Our method learns a spatio-temporal embedding integrating cues from appearance, motion, and geometry; a 3D causal convolutional network models motion, and a monocular…
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or…
We present a novel method to fuse the power of deep networks with the computational efficiency of geometric and probabilistic localization algorithms. In contrast to other methods that completely replace a classical visual estimator with a…
3D human motion prediction is a research area of high significance and a challenge in computer vision. It is useful for the design of many applications including robotics and autonomous driving. Traditionally, autogregressive models have…
This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most…
The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a…
Despite decades of research, understanding human manipulation activities is, and has always been, one of the most attractive and challenging research topics in computer vision and robotics. Recognition and prediction of observed human…
In this work, we address the lack of 3D understanding of generative neural networks by introducing a persistent 3D feature embedding for view synthesis. To this end, we propose DeepVoxels, a learned representation that encodes the…