Related papers: SpecTrack: Learned Multi-Rotation Tracking via Spe…

Object detection and tracking is a key task in autonomy. Specifically, 3D object detection and tracking have been an emerging hot topic recently. Although various methods have been proposed for object detection, uncertainty in the 3D…

Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture…

The encoding of the target in object tracking moves from the coarse bounding-box to fine-grained segmentation map recently. Revisiting de facto real-time approaches that are capable of predicting mask during tracking, we observed that they…

Robust 6D pose estimation of novel objects under challenging illumination remains a significant challenge, often requiring a trade-off between accurate initial pose estimation and efficient real-time tracking. We present a unified framework…

Occlusion is a long-standing problem that causes many modern tracking methods to be erroneous. In this paper, we address the occlusion problem by exploiting the current and future possible locations of the target object from its past…

This paper addresses the problem of monocular 3D human shape and pose estimation from an RGB image. Despite great progress in this field in terms of pose prediction accuracy, state-of-the-art methods often predict inaccurate body shapes. We…

Most tracking-by-detection methods employ a local search window around the predicted object location in the current frame assuming the previous location is accurate, the trajectory is smooth, and the computational capacity permits a search…

Multiple object tracking faces several challenges that may be alleviated with trajectory information. Knowing the posterior locations of an object helps disambiguating and solving situations such as occlusions, re-identification, and…

Real-time tracking of previously unseen, highly dynamic objects in contact-rich scenes, such as during dexterous in-hand manipulation, remains a major challenge. Pure vision-based approaches often fail under heavy occlusions due to frequent…

Tracking the 6D pose of objects in video sequences is important for robot manipulation. Most prior efforts, however, often assume that the target object's CAD model, at least at a category-level, is available for offline training or during…

Path tracing offers high-fidelity rendering but remains impractical for real-time applications due to slow convergence and noise. We present a dynamic foveated path tracing technique that leverages visual perception by reducing sampling…

Current deep models provide remarkable object detection in terms of object classification and localization. However, estimating object rotation with respect to other visual objects in the visual context of an input image still lacks deep…

Accurate detection and tracking of objects is vital for effective video understanding. In previous work, the two tasks have been combined in a way that tracking is based heavily on detection, but the detection benefits marginally from the…

6D pose estimation of textureless shiny objects has become an essential problem in many robotic applications. Many pose estimators require high-quality depth data, often measured by structured light cameras. However, when objects have shiny…

Adaptive robots in dynamic production environments require robust perception capabilities, including 6D pose estimation and multi-object tracking. To address limitations in real-world data dependency, noise robustness, and spatiotemporal…

This paper introduces key machine learning operations that allow the realization of robust, joint 6D pose estimation of multiple instances of objects either densely packed or in unstructured piles from RGB-D data. The first objective is to…

Articulated objects are prevalent in daily life and robotic manipulation tasks. However, compared to rigid objects, pose tracking for articulated objects remains an underexplored problem due to their inherent kinematic constraints. To…

Methods tackling multi-object tracking need to estimate the number of targets in the sensing area as well as to estimate their continuous state. While the majority of existing methods focus on data association, precise state (3D pose)…

To build commercial robots, skid-steering mechanical design is of increased popularity due to its manufacturing simplicity and unique mechanism. However, these also cause significant challenges on software and algorithm design, especially…

A new high-precision eye-tracking method has been demonstrated recently by tracking the motion of iris features rather than by exploiting pupil edges. While the method provides high precision, it suffers from temporal drift, an inability to…