MT-Net Submission to the Waymo 3D Detection Leaderboard
This work addresses 3D detection for autonomous vehicles, representing an incremental improvement over existing methods.
The paper tackles 3D object detection for autonomous driving by improving the Centerpoint architecture with multi-scale features and optimal transport-based target assignment, achieving 78.45 mAPH and ranking 4th on the Waymo leaderboard.
In this technical report, we introduce our submission to the Waymo 3D Detection leaderboard. Our network is based on the Centerpoint architecture, but with significant improvements. We design a 2D backbone to utilize multi-scale features for better detecting objects with various sizes, together with an optimal transport-based target assignment strategy, which dynamically assigns richer supervision signals to the detection candidates. We also apply test-time augmentation and model-ensemble for further improvements. Our submission currently ranks 4th place with 78.45 mAPH on the Waymo 3D Detection leaderboard.