GSV2X：面向鲁棒路侧感知的几何感知不确定性建模与正交融合
GSV2X: Geometry-Aware Uncertainty Modeling and Orthogonal Fusion for Robust Roadside Perception
把2D图像特征建模为3D高斯分布并注入相机几何引导的可学习扰动，为BEV融合提供了一种显式吸收标定误差的手段；正交约束注意力用于解耦冗余模态特征，可迁移到任何相机-激光雷达融合的BEV感知框架。
原文依据 we lift 2D image features into a unified Bird's-Eye-View (BEV) space by representing them as 3D Gaussian distributions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论来自多视角路侧传感器的可靠三维感知依赖于相机与激光雷达数据的鲁棒融合，而几何失配与传感器标定误差使这一任务变得复杂。本文提出 GSV2X，一个通过两项核心贡献应对上述挑战的融合框架。首先，为获得对空间不确定性的鲁棒性，我们将二维图像特征表示为三维高斯分布，从而将其提升到统一的鸟瞰图（BEV）空间。通过引入由相机几何引导的可学习扰动，我们的模型显式地考虑了潜在的标定不准确问题。其次，为最大化模态间的协同效应，我们提出一种新的正交融合模块。该模块采用受约束的注意力机制，强制相机特征与激光雷达特征之间保持正交，从而有效解耦冗余信息并促进互补表征的学习。在具有挑战性的 RCooper 数据集上的大量实验表明，GSV2X 在多视角路侧感知上取得了新的最优性能，并在复杂的真实场景中展现出显著的鲁棒性。
英文原文摘要 1127 字符
Reliable 3D perception from multi-view roadside sensors hinges on the robust fusion of camera and LiDAR data, a task complicated by geometric misalignments and sensor calibration errors. This paper presents GSV2X, a fusion framework that tackles these challenges through two core contributions. First, to achieve robustness against spatial uncertainty, we lift 2D image features into a unified Bird's-Eye-View (BEV) space by representing them as 3D Gaussian distributions. By incorporating learnable perturbations guided by camera geometry, our model explicitly accounts for potential calibration inaccuracies. Second, to maximize the synergy between modalities, we propose a new orthogonal fusion module. This module employs constrained attention to enforce orthogonality between camera and LiDAR features, effectively disentangling redundant information and promoting the learning of complementary representations. Extensive experiments on the challenging RCooper dataset demonstrate that GSV2X sets a new state-of-the-art in multi-view roadside perception and exhibits remarkable robustness in complex, real-world scenarios.