Related papers: GelFlow: Self-supervised Learning of Optical Flow …
Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…
Modern optical flow methods make use of salient scene feature points detected and matched within the scene as a basis for sparse-to-dense optical flow estimation. Current feature detectors however either give sparse, non uniform point…
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications. Generally, video super-resolution contains a significant component, i.e., motion…
Teaching robots to fold, drape, or reposition deformable objects such as cloth will unlock a variety of automation applications. While remarkable progress has been made for rigid object manipulation, manipulating deformable objects poses…
We present a tactile sensing method enabled by the mechanical compliance of soft robots; an externally attachable photoreflective module reads surface deformation of silicone skin to estimate contact force without embedding tactile…
The images captured by vision-based tactile sensors carry information about high-resolution tactile fields, such as the distribution of the contact forces applied to their soft sensing surface. However, extracting the information encoded in…
We present DDFlow, a data distillation approach to learning optical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher network, and uses these predictions as annotations to guide a student network…
Simulation is widely used in robotics for system verification and large-scale data collection. However, simulating sensors, including tactile sensors, has been a long-standing challenge. In this paper, we propose Taxim, a realistic and…
Large displacement optical flow is an integral part of many computer vision tasks. Variational optical flow techniques based on a coarse-to-fine scheme interpolate sparse matches and locally optimize an energy model conditioned on colour,…
Tactile sensing is essential to the human perception system, so as to robot. In this paper, we develop a novel optical-based tactile sensor "FingerVision" with effective signal processing algorithms. This sensor is composed of soft skin…
Deconvolution is the most commonly used image processing method to remove the blur caused by the point-spread-function (PSF) in optical imaging systems. While this method has been successful in deblurring, it suffers from several…
Deep convolutional neural networks (DCNN) have recently shown promising results in low-level computer vision problems such as optical flow and disparity estimation, but still, have much room to further improve their performance. In this…
Although conventional GelSight-based tactile and force/torque sensors excel in detecting objects' geometry and texture information while simultaneously sensing multi-axis forces, their performance is limited by the camera's lower frame…
We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlike existing approaches which rely on brightness constancy and…
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…
Unsupervised video object segmentation (VOS) aims to detect the most prominent object in a video. Recently, two-stream approaches that leverage both RGB images and optical flow have gained significant attention, but their performance is…
Computing optical flow is a fundamental problem in computer vision. However, deep learning-based optical flow techniques do not perform well for non-rigid movements such as those found in faces, primarily due to lack of the training data…
Collocated tactile sensing is a fundamental enabling technology for dexterous manipulation. However, deformable sensors introduce complex dynamics between the robot, grasped object, and environment that must be considered for fine…
Deep learning and reinforcement learning methods have been shown to enable learning of flexible and complex robot controllers. However, the reliance on large amounts of training data often requires data collection to be carried out in…
Humans perceive the world by interacting with objects, which often happens in a dynamic way. For example, a human would shake a bottle to guess its content. However, it remains a challenge for robots to understand many dynamic signals…