用姿态网络生成通道级运动特征，实现高效动态物体分割。
Channel-wise Motion Features for Efficient Motion Segmentation
- 仅用姿态网络提取通道级运动特征，避免多子网计算开销。
- 在KITTI和Cityscapes上达到4倍于主流模型的帧率，参数量减至25%。
- 适合对实时性要求高的自动驾驶等机器人场景。
在自动驾驶等安全关键型机器人应用中，需实时准确检测所有动态物体。运动分割通过无类别地识别场景中的动态对象提供解决方案。近期多数模型联合使用深度、位姿、光流和场景流子网络，导致整体计算成本高，难以满足实时需求。本文提出一种基于代价体积的新型运动特征表示——通道级运动特征（Channel-wise Motion Features）。该方法仅依赖姿态网络，通过提取特征图中每个实例的深度特征并捕捉场景3D运动信息，显著提升效率。实验表明，在KITTI与Cityscapes数据集及VCAS-Motion数据集上，本方法实现约4倍于当前最优模型的帧率（FPS），同时参数量降至约25%，且精度相当。
原文摘要 · Abstract (English)
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$\%$.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。