MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
This work addresses the problem of accurate 3D detection for autonomous driving and robotics, representing an incremental improvement with novel method components.
The paper tackles 3D temporal object detection using point cloud sequences by proposing MPPNet, a framework with proxy points for multi-frame feature encoding and interactions, which outperforms state-of-the-art methods by large margins on the Waymo Open dataset for both short and long sequences.
Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots. In this paper, we present a flexible and high-performance 3D detection framework, named MPPNet, for 3D temporal object detection with point cloud sequences. We propose a novel three-hierarchy framework with proxy points for multi-frame feature encoding and interactions to achieve better detection. The three hierarchies conduct per-frame feature encoding, short-clip feature fusion, and whole-sequence feature aggregation, respectively. To enable processing long-sequence point clouds with reasonable computational resources, intra-group feature mixing and inter-group feature attention are proposed to form the second and third feature encoding hierarchies, which are recurrently applied for aggregating multi-frame trajectory features. The proxy points not only act as consistent object representations for each frame, but also serve as the courier to facilitate feature interaction between frames. The experiments on large Waymo Open dataset show that our approach outperforms state-of-the-art methods with large margins when applied to both short (e.g., 4-frame) and long (e.g., 16-frame) point cloud sequences. Code is available at https://github.com/open-mmlab/OpenPCDet.