用高斯分布建模鱼眼图像深度不确定性，直接生成带置信度的鸟瞰语义图。
FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception
- 像素转3D用高斯参数化，显式建模几何不确定性
- 在严重畸变下实现87.75%可行驶区域、57.26%车辆分割IoU
- 无需去畸变或投影校正，端到端处理多鱼眼图像
由于广角投影固有的极端非线性畸变、遮挡和深度模糊，从鱼眼图像中实现准确的鸟瞰图（BEV）语义分割仍具挑战。本文提出一种畸变感知的BEV分割框架，直接处理多相机高分辨率鱼眼图像，利用校准的几何反投影和每像素深度分布估计。每个图像像素通过高斯参数化提升至3D空间，预测空间均值与各向异性协方差，以显式建模几何不确定性。投影后的3D高斯通过可微分点阵融合生成BEV表示，产生连续且带有不确定性感知的语义图，无需去畸变或透视校正。大量实验表明，在复杂停车及城市驾驶场景中表现优异，严重鱼眼畸变下可行驶区域分割达到87.75% IoU，车辆分割达57.26% IoU。
原文摘要 · Abstract (English)
Accurate BEV semantic segmentation from fisheye imagery remains challenging due to extreme non-linear distortion, occlusion, and depth ambiguity inherent to wide-angle projections. We present a distortion-aware BEV segmentation framework that directly processes multi-camera high-resolution fisheye images,utilizing calibrated geometric unprojection and per-pixel depth distribution estimation. Each image pixel is lifted into 3D space via Gaussian parameterization, predicting spatial means and anisotropic covariances to explicitly model geometric uncertainty. The projected 3D Gaussians are fused into a BEV representation via differentiable splatting, producing continuous, uncertainty-aware semantic maps without requiring undistortion or perspective rectification. Extensive experiments demonstrate strong segmentation performance on complex parking and urban driving scenarios, achieving IoU scores of 87.75% for drivable regions and 57.26% for vehicles under severe fisheye distortion and diverse environmental conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。