AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds

TL;DR

AFDetV2 introduces a single-stage, anchor-free 3D object detection network that achieves state-of-the-art accuracy and efficiency by redesigning the detection pipeline to produce accurate boxes and effective rescoring, eliminating the need for a second stage.

Contribution

The paper proposes AFDetV2, a novel single-stage 3D detection method that surpasses two-stage methods in accuracy and efficiency, challenging the necessity of the second stage in point cloud detection.

Findings

Achieves state-of-the-art results on Waymo and nuScenes datasets.

Wins 1st place in the Waymo Open Dataset Challenge 2021.

Demonstrates second stage refinement is unnecessary with the proposed design.

Abstract

There have been two streams in the 3D detection from point clouds: single-stage methods and two-stage methods. While the former is more computationally efficient, the latter usually provides better detection accuracy. By carefully examining the two-stage approaches, we have found that if appropriately designed, the first stage can produce accurate box regression. In this scenario, the second stage mainly rescores the boxes such that the boxes with better localization get selected. From this observation, we have devised a single-stage anchor-free network that can fulfill these requirements. This network, named AFDetV2, extends the previous work by incorporating a self-calibrated convolution block in the backbone, a keypoint auxiliary supervision, and an IoU prediction branch in the multi-task head. As a result, the detection accuracy is drastically boosted in the single-stage. To evaluate our approach, we have conducted extensive experiments on the Waymo Open Dataset and the nuScenes Dataset. We have observed that our AFDetV2 achieves the state-of-the-art results on these two datasets, superior to all the prior arts, including both the single-stage and the two-stage 3D detectors. AFDetV2 won the 1st place in the Real-Time 3D Detection of the Waymo Open Dataset Challenge 2021. In addition, a variant of our model AFDetV2-Base was entitled the "Most Efficient Model" by the Challenge Sponsor, showing a superior computational efficiency. To demonstrate the generality of this single-stage method, we have also applied it to the first stage of the two-stage networks. Without exception, the results show that with the strengthened backbone and the rescoring approach, the second stage refinement is no longer needed.