OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving

TL;DR

OcRFDet introduces object-centric radiance fields to improve multi-view 3D object detection by focusing on foreground objects and enhancing feature representations, leading to state-of-the-art results on nuScenes.

Contribution

The paper proposes object-centric radiance fields and height-aware opacity attention to improve 3D detection accuracy in autonomous driving.

Findings

Achieves 57.2% mAP and 64.8% NDS on nuScenes

Outperforms previous state-of-the-art methods

Demonstrates the effectiveness of foreground-focused radiance modeling

Abstract

Current multi-view 3D object detection methods typically transfer 2D features into 3D space using depth estimation or 3D position encoder, but in a fully data-driven and implicit manner, which limits the detection performance. Inspired by the success of radiance fields on 3D reconstruction, we assume they can be used to enhance the detector's ability of 3D geometry estimation. However, we observe a decline in detection performance, when we directly use them for 3D rendering as an auxiliary task. From our analysis, we find the performance drop is caused by the strong responses on the background when rendering the whole scene. To address this problem, we propose object-centric radiance fields, focusing on modeling foreground objects while discarding background noises. Specifically, we employ Object-centric Radiance Fields (OcRF) to enhance 3D voxel features via an auxiliary task of rendering foreground objects. We further use opacity - the side-product of rendering- to enhance the 2D foreground BEV features via Height-aware Opacity-based Attention (HOA), where attention maps at different height levels are generated separately via multiple networks in parallel. Extensive experiments on the nuScenes validation and test datasets demonstrate that our OcRFDet achieves superior performance, outperforming previous state-of-the-art methods with 57.2$\%$ mAP and 64.8$\%$ NDS on the nuScenes test benchmark. Code will be available at https://github.com/Mingqj/OcRFDet.