Surface-biased Multi-Level Context 3D Object Detection

TL;DR

This paper introduces a surface-biased, multi-level context 3D object detection method that leverages self-attention to improve feature extraction and outperform existing detectors in complex 3D scenes.

Contribution

It proposes a novel 3D object detector combining surface-biased feature extraction with multi-level self-attention, enhancing detection accuracy over prior methods.

Findings

Outperforms state-of-the-art 3D detectors on ScanNet dataset

Self-attention at multiple levels improves feature representation

Surface-biased features effectively capture object cues

Abstract

Object detection in 3D point clouds is a crucial task in a range of computer vision applications including robotics, autonomous cars, and augmented reality. This work addresses the object detection task in 3D point clouds using a highly efficient, surface-biased, feature extraction method (wang2022rbgnet), that also captures contextual cues on multiple levels. We propose a 3D object detector that extracts accurate feature representations of object candidates and leverages self-attention on point patches, object candidates, and on the global scene in 3D scene. Self-attention is proven to be effective in encoding correlation information in 3D point clouds by (xie2020mlcvnet). While other 3D detectors focus on enhancing point cloud feature extraction by selectively obtaining more meaningful local features (wang2022rbgnet) where contextual information is overlooked. To this end, the proposed architecture uses ray-based surface-biased feature extraction and multi-level context encoding to outperform the state-of-the-art 3D object detector. In this work, 3D detection experiments are performed on scenes from the ScanNet dataset whereby the self-attention modules are introduced one after the other to isolate the effect of self-attention at each level.