Recently 3D object detection from surround-view images has made notable advancements with its low deployment cost. However, most works have primarily focused on close perception range while leaving long-range detection less explored. Expanding existing methods directly to cover long distances poses challenges such as heavy computation costs and unstable convergence. To address these limitations, this paper proposes a novel sparse query-based framework, dubbed Far3D. By utilizing high-quality 2D object priors, we generate 3D adaptive queries that complement the 3D global queries. To efficiently capture discriminative features across different views and scales for long-range objects, we introduce a perspective-aware aggregation module. Additionally, we propose a range-modulated 3D denoising approach to address query error propagation and mitigate convergence issues in long-range tasks. Significantly, Far3D demonstrates SoTA performance on the challenging Argoverse 2 dataset, covering a wide range of 150 meters, surpassing several LiDAR-based approaches. Meanwhile, Far3D exhibits superior performance compared to previous methods on the nuScenes dataset. The code is available at https://github.com/megvii-research/Far3D.
@article{arxiv.2308.09616,
title = {Far3D: Expanding the Horizon for Surround-view 3D Object Detection},
author = {Xiaohui Jiang and Shuailin Li and Yingfei Liu and Shihao Wang and Fan Jia and Tiancai Wang and Lijin Han and Xiangyu Zhang},
journal= {arXiv preprint arXiv:2308.09616},
year = {2023}
}