OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection

TL;DR

OCBEV introduces an object-centric BEV transformer that enhances multi-view 3D detection by effectively modeling moving objects, leading to state-of-the-art results and faster training convergence on nuScenes.

Contribution

The paper proposes OCBEV, a novel object-centric BEV transformer with three key designs for improved temporal and spatial modeling of moving objects in 3D detection.

Findings

Achieves state-of-the-art 1.5 NDS points on nuScenes

Faster convergence, requiring half the training iterations

Outperforms traditional BEVFormer in accuracy and efficiency

Abstract

Multi-view 3D object detection is becoming popular in autonomous driving due to its high effectiveness and low cost. Most of the current state-of-the-art detectors follow the query-based bird's-eye-view (BEV) paradigm, which benefits from both BEV's strong perception power and end-to-end pipeline. Despite achieving substantial progress, existing works model objects via globally leveraging temporal and spatial information of BEV features, resulting in problems when handling the challenging complex and dynamic autonomous driving scenarios. In this paper, we proposed an Object-Centric query-BEV detector OCBEV, which can carve the temporal and spatial cues of moving targets more effectively. OCBEV comprises three designs: Object Aligned Temporal Fusion aligns the BEV feature based on ego-motion and estimated current locations of moving objects, leading to a precise instance-level feature fusion. Object Focused Multi-View Sampling samples more 3D features from an adaptive local height ranges of objects for each scene to enrich foreground information. Object Informed Query Enhancement replaces part of pre-defined decoder queries in common DETR-style decoders with positional features of objects on high-confidence locations, introducing more direct object positional priors. Extensive experimental evaluations are conducted on the challenging nuScenes dataset. Our approach achieves a state-of-the-art result, surpassing the traditional BEVFormer by 1.5 NDS points. Moreover, we have a faster convergence speed and only need half of the training iterations to get comparable performance, which further demonstrates its effectiveness.