Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection

TL;DR

This paper introduces a shape prior non-uniform sampling strategy for real-time stereo 3D object detection, emphasizing outer region sampling to improve accuracy without extra supervision or speed loss.

Contribution

It proposes a shape prior non-uniform sampling method and a semantic-enhanced FCE module to improve 3D detection accuracy in real-time without additional supervision.

Findings

Achieves 2.57% AP3d improvement over baseline RTS3D

Outperforms state-of-the-art methods without extra supervision

Maintains real-time detection speed

Abstract

Pseudo-LiDAR based 3D object detectors have gained popularity due to their high accuracy. However, these methods need dense depth supervision and suffer from inferior speed. To solve these two issues, a recently introduced RTS3D builds an efficient 4D Feature-Consistency Embedding (FCE) space for the intermediate representation of object without depth supervision. FCE space splits the entire object region into 3D uniform grid latent space for feature sampling point generation, which ignores the importance of different object regions. However, we argue that, compared with the inner region, the outer region plays a more important role for accurate 3D detection. To encode more information from the outer region, we propose a shape prior non-uniform sampling strategy that performs dense sampling in outer region and sparse sampling in inner region. As a result, more points are sampled from the outer region and more useful features are extracted for 3D detection. Further, to enhance the feature discrimination of each sampling point, we propose a high-level semantic enhanced FCE module to exploit more contextual information and suppress noise better. Experiments on the KITTI dataset are performed to show the effectiveness of the proposed method. Compared with the baseline RTS3D, our proposed method has 2.57% improvement on AP3d almost without extra network parameters. Moreover, our proposed method outperforms the state-of-the-art methods without extra supervision at a real-time speed.