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

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.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Datasets


Introduced in the Paper:

TbD-3D

Used in the Paper:

TbD Falling Objects

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Video Super-Resolution Falling Objects TbD-3D SSIM 0.671 # 2
PSNR 23.42 # 2
TIoU 0.539 # 1
Video Super-Resolution TbD TbD-3D SSIM 0.674 # 1
PSNR 25.21 # 2
TIoU 0.542 # 2
Video Super-Resolution TbD-3D TbD-3D SSIM 0.651 # 2
PSNR 23.13 # 2
TIoU 0.598 # 2

Methods