CVNov 25, 2019

Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects

arXiv:1911.10927v121 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the challenge of accurately tracking fast-moving objects with appearance changes for applications like robotics and computer vision, presenting an incremental improvement with a new dataset.

The paper tackles the problem of tracking fast-moving objects in 6D pose and appearance with sub-frame precision, achieving realistic temporal super-resolution and precise shape estimation. It introduces TbD-3D, a method that estimates 3D motion trajectory, pose, and appearance changes using a novel reconstruction algorithm for deblurring and matting.

We propose a novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a time step that is a fraction of the video frame exposure time. The sub-frame object localization and appearance estimation allows realistic temporal super-resolution and precise shape estimation. The method, called TbD-3D (Tracking by Deblatting in 3D) relies on a novel reconstruction algorithm which solves a piece-wise deblurring and matting problem. The 3D rotation is estimated by minimizing the reprojection error. As a second contribution, we present a new challenging dataset with fast moving objects that change their appearance and distance to the camera. High speed camera recordings with zero lag between frame exposures were used to generate videos with different frame rates annotated with ground-truth trajectory and pose.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes