arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.10042cs.CV
收藏

用于端到端3D目标检测的抑制和优化框架

Suppress-and-Refine Framework for End-to-End 3D Object Detection

State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室);Fabu Inc.

Zili Liu, Guodong Xu, Honghui Yang, Minghao Chen, Kuoliang Wu, Zheng Yang, Haifeng Liu, Deng Cai

摘要:

基于Hough投票的三维物体检测器取得了很大的成功,并衍生出许多后续工作。尽管不断刷新检测精度,但这些作品受到用于消除冗余框的手工制作组件的影响,因此是非端到端且耗时。在这项工作中,我们提出了一个抑制和完善的框架,以消除这些手工制作的组件。为了充分利用全分辨率信息并实现实时速度,它直接消耗特征点和冗余的3D建议。具体来说,它首先抑制有噪声的3D特征点,然后将它们馈送到3D提案中,以进行后续的ROI感知细化。通过门控机制来构建精细的建议特征和自注意力机制来建模关系,我们的方法可以以端到端的方式以小的计算预算产生高质量的预测。为此,我们在VoteNet的基础上提出了第一个完全端到端的3D检测器SRDet。它以有史以来最快的速度在具有挑战性的ScanNetV 2和SUN RGB-D数据集上实现了最先进的性能。我们的代码将在https://github.com/ZJULearning/SRDet上提供。

英文摘要:

3D object detector based on Hough voting achieves great success and derives many follow-up works. Despite constantly refreshing the detection accuracy, these works suffer from handcrafted components used to eliminate redundant boxes, and thus are non-end-to-end and time-consuming. In this work, we propose a suppress-and-refine framework to remove these handcrafted components. To fully utilize full-resolution information and achieve real-time speed, it directly consumes feature points and redundant 3D proposals. Specifically, it first suppresses noisy 3D feature points and then feeds them to 3D proposals for the following RoI-aware refinement. With the gating mechanism to build fine proposal features and the self-attention mechanism to model relationships, our method can produce high-quality predictions with a small computation budget in an end-to-end manner. To this end, we present the first fully end-to-end 3D detector, SRDet, on the basis of VoteNet. It achieves state-of-the-art performance on the challenging ScanNetV2 and SUN RGB-D datasets with the fastest speed ever. Our code will be available at https://github.com/ZJULearning/SRDet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑