arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.01404cs.CV
收藏

Gaussian-Det:学习闭合表面高斯以实现3D目标检测

Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection

Tsinghua University(清华大学)

Hongru Yan, Yu Zheng, Yueqi Duan

AI总结:

针对3D目标检测,提出Gaussian-Det方法,以高斯溅射为连续表面表示,设计闭合推断模块处理离群点,实验表明其在平均精度和召回率上优于现有方法。

摘要:

包裹我们身体的皮肤、覆盖沙发的皮革、涂覆汽车的金属板——这表明物体由一系列连续表面包围,为目标性推断提供了丰富的几何先验。本文提出Gaussian-Det,将高斯溅射(Gaussian Splatting)作为表面表示用于多视图3D目标检测。与通过离散位置数据描述物体的现有单目或NeRF基方法不同,Gaussian-Det通过将输入高斯建模为大量部分表面的特征描述符,以连续方式表示物体。此外,为解决高斯溅射固有引入的大量离群点,我们设计了闭合推断模块(CIM)用于基于表面的全面目标性推断。CIM首先针对高斯溅射的欠定性质估计部分表面的概率特征残差,然后将其融合为物体候选的整体表面表示。通过这种方式,Gaussian-Det利用的表面信息既作为目标性质量与可靠性的先验,又作为候选优化的信息基础。在合成与真实数据集上的实验表明,Gaussian-Det在平均精度和召回率方面均优于多种现有方法。

英文摘要:

Skins wrapping around our bodies, leathers covering over the sofa, sheet metal coating the car - it suggests that objects are enclosed by a series of continuous surfaces, which provides us with informative geometry prior for objectness deduction. In this paper, we propose Gaussian-Det which leverages Gaussian Splatting as surface representation for multi-view based 3D object detection. Unlike existing monocular or NeRF-based methods which depict the objects via discrete positional data, Gaussian-Det models the objects in a continuous manner by formulating the input Gaussians as feature descriptors on a mass of partial surfaces. Furthermore, to address the numerous outliers inherently introduced by Gaussian splatting, we accordingly devise a Closure Inferring Module (CIM) for the comprehensive surface-based objectness deduction. CIM firstly estimates the probabilistic feature residuals for partial surfaces given the underdetermined nature of Gaussian Splatting, which are then coalesced into a holistic representation on the overall surface closure of the object proposal. In this way, the surface information Gaussian-Det exploits serves as the prior on the quality and reliability of objectness and the information basis of proposal refinement. Experiments on both synthetic and real-world datasets demonstrate that Gaussian-Det outperforms various existing approaches, in terms of both average precision and recall.

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。

↑