Gaussian-Det
Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection
Hongru Yan* Yu Zheng* Yueqi Duan
Tsinghua University
[Technical Report] [Code]
Abstract & Method
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.
Results
Citation
If you find this useful for your research, please use the following.
@inproceedings{yan2024gaussian,
title={Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection},
author={Yan, Hongru and Zheng, Yu and Duan, Yueqi},
journal={arXiv preprint arXiv:2410.01404},
year={2024}
}
|