3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds

TL;DR

This paper introduces 3D IoU-Net, a novel point cloud 3D object detection method that predicts IoU for improved confidence scoring, utilizing innovative feature learning and alignment techniques, achieving state-of-the-art results on KITTI.

Contribution

The paper proposes a 3D IoU prediction branch with IoU sensitive feature learning, an IoU alignment operation, and novel modules for geometric encoding and perspective-invariant prediction, advancing 3D detection accuracy.

Findings

Achieves state-of-the-art performance on KITTI benchmark.

Introduces IoU-aware confidence scoring for NMS.

Demonstrates improved IoU prediction accuracy.

Abstract

Most existing point cloud based 3D object detectors focus on the tasks of classification and box regression. However, another bottleneck in this area is achieving an accurate detection confidence for the Non-Maximum Suppression (NMS) post-processing. In this paper, we add a 3D IoU prediction branch to the regular classification and regression branches. The predicted IoU is used as the detection confidence for NMS. In order to obtain a more accurate IoU prediction, we propose a 3D IoU-Net with IoU sensitive feature learning and an IoU alignment operation. To obtain a perspective-invariant prediction head, we propose an Attentive Corner Aggregation (ACA) module by aggregating a local point cloud feature from each perspective of eight corners and adaptively weighting the contribution of each perspective with different attentions. We propose a Corner Geometry Encoding (CGE) module for geometry information embedding. To the best of our knowledge, this is the first time geometric embedding information has been introduced in proposal feature learning. These two feature parts are then adaptively fused by a multi-layer perceptron (MLP) network as our IoU sensitive feature. The IoU alignment operation is introduced to resolve the mismatching between the bounding box regression head and IoU prediction, thereby further enhancing the accuracy of IoU prediction. The experimental results on the KITTI car detection benchmark show that 3D IoU-Net with IoU perception achieves state-of-the-art performance.