This paper presents a comprehensive survey on vision-based robotic grasping. We
conclude three key tasks during vision-based robotic grasping, which are object localization …

Object pose detection and tracking has recently attracted increasing attention due to its wide
applications in many areas, such as autonomous driving, robotics, and augmented reality …

Abstract 6D pose estimation from a single RGB image is a fundamental task in computer
vision. The current top-performing deep learning-based methods rely on an indirect strategy …

Locating 3D objects from a single RGB image via Perspective-n-Points (PnP) is a long-
standing problem in computer vision. Driven by end-to-end deep learning, recent studies …

We introduce an approach for recovering the 6D pose of multiple known objects in a scene
captured by a set of input images with unknown camera viewpoints. First, we present a …

In this work, we present FFB6D, a full flow bidirectional fusion network designed for 6D pose
estimation from a single RGBD image. Our key insight is that appearance information in the …

We propose a new method named OnePose for object pose estimation. Unlike existing
instance-level or category-level methods, OnePose does not rely on CAD models and can …

Establishing correspondences from image to 3D has been a key task of 6DoF object pose
estimation for a long time. To predict pose more accurately, deeply learned dense maps …

Removing outlier correspondences is one of the critical steps for successful feature-based
point cloud registration. Despite the increasing popularity of introducing deep learning …

We introduce DexYCB, a new dataset for capturing hand grasping of objects. We first
compare DexYCB with a related one through cross-dataset evaluation. We then present a …