Channel-wise Motion Features for Efficient Motion Segmentation

TL;DR

This paper introduces Channel-wise Motion Features, a novel efficient motion segmentation method that significantly improves real-time performance and reduces model complexity without sacrificing accuracy.

Contribution

It proposes a cost-volume-based motion feature representation that uses only a Pose Network, reducing computational cost and parameters while maintaining accuracy.

Findings

Achieves 4x the FPS of state-of-the-art models on KITTI and Cityscapes datasets.

Reduces model parameters to about 25% of existing models.

Maintains comparable accuracy with significantly improved efficiency.

Abstract

For safety-critical robotics applications such as autonomous driving, it is important to detect all required objects accurately in real-time. Motion segmentation offers a solution by identifying dynamic objects from the scene in a class-agnostic manner. Recently, various motion segmentation models have been proposed, most of which jointly use subnetworks to estimate Depth, Pose, Optical Flow, and Scene Flow. As a result, the overall computational cost of the model increases, hindering real-time performance. In this paper, we propose a novel cost-volume-based motion feature representation, Channel-wise Motion Features. By extracting depth features of each instance in the feature map and capturing the scene's 3D motion information, it offers enhanced efficiency. The only subnetwork used to build Channel-wise Motion Features is the Pose Network, and no others are required. Our method not only achieves about 4 times the FPS of state-of-the-art models in the KITTI Dataset and Cityscapes of the VCAS-Motion Dataset, but also demonstrates equivalent accuracy while reducing the parameters to about 25$\%$.