BEVNeXt:复兴密集 BEV 框架以用于 3D 目标检测
BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection
AI总结:
本文提出现代化密集 BEV 框架 BEVNeXt,通过引入 CRF 调制深度估计、扩展感受野的时间聚合及两阶段目标解码器,在 nuScenes 测试集上以 64.2 NDS 达到最先进水平。
摘要:
最近,基于查询的 Transformer 解码器的兴起正在重塑基于摄像头的 3D 目标检测。这些基于查询的解码器正超越传统的密集 BEV(鸟瞰图)方法。然而,我们认为密集 BEV 框架仍然很重要,因为它们在深度估计和目标定位方面具有出色的能力,能够准确且全面地描绘 3D 场景。本文旨在通过引入我们提出的增强组件来解决现有基于密集 BEV 的 3D 目标检测器的缺陷,包括:一个强制执行目标级一致性的 CRF 调制深度估计模块,一个具有扩展感受野的长期时间聚合模块,以及一个结合透视技术与 CRF 调制深度嵌入的两阶段目标解码器。这些增强带来了一个名为 BEVNeXt 的“现代化”密集 BEV 框架。在 nuScenes 基准上,BEVNeXt 在各种设置下均优于基于 BEV 和基于查询的框架,在 nuScenes 测试集上取得了 64.2 NDS 的最先进结果。代码将发布于 https://github.com/woxihuanjiangguo/BEVNeXt。
英文摘要:
Recently, the rise of query-based Transformer decoders is reshaping camera-based 3D object detection. These query-based decoders are surpassing the traditional dense BEV (Bird's Eye View)-based methods. However, we argue that dense BEV frameworks remain important due to their outstanding abilities in depth estimation and object localization, depicting 3D scenes accurately and comprehensively. This paper aims to address the drawbacks of the existing dense BEV-based 3D object detectors by introducing our proposed enhanced components, including a CRF-modulated depth estimation module enforcing object-level consistencies, a long-term temporal aggregation module with extended receptive fields, and a two-stage object decoder combining perspective techniques with CRF-modulated depth embedding. These enhancements lead to a "modernized" dense BEV framework dubbed BEVNeXt. On the nuScenes benchmark, BEVNeXt outperforms both BEV-based and query-based frameworks under various settings, achieving a state-of-the-art result of 64.2 NDS on the nuScenes test set. Code will be available at \url{https://github.com/woxihuanjiangguo/BEVNeXt}.
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。