SCE-Depth：面向宽视场深度估计的球面复眼框架
SCE-Depth: A Spherical Compound Eye Framework for Wide FOV Depth Estimation
把球面成像数据直接在 HEALPix 网格上用球面网络处理，避免鱼眼/全景到平面的模态转换误差；其球面 Sobel 算子（SGFE）与球面梯度损失（SGL）可迁移到任何宽 FOV 球面深度或稠密预测任务。
原文依据 processes spherical images natively on a HEALPix grid using a spherical neural network
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在自动驾驶、机器人视觉与无人机控制等应用中，宽视场下的精确深度估计需求迫切。生物复眼为宽视场（FOV）深度估计提供了灵感，但其人工实现面临模态失配的挑战。具体而言，球面成像数据与平面神经网络难以良好对齐，从而降低了学习效率。为此，我们提出 SCE-Depth，一种面向球面复眼深度估计的仿生框架，它借助球面神经网络在 HEALPix 网格上原生处理球面图像。该方法实现了统一的 180 度视场，同时避免了模态转换通常引入的误差。此外，我们从相邻小眼的视场重叠中识别出一种对深度敏感的梯度特征。为利用该特征，我们引入一种称为球面梯度特征提取器（SGFE）的球面 Sobel 算子以及相应的球面梯度损失（SGL），二者在 HEALPix 网格上联合提取梯度特征，从而实现梯度感知的深度预测。大量基准实验表明，这些策略使 SCE-Depth 相比基于鱼眼的基线显著降低了深度估计误差，在周边区域的精度提升尤为明显。我们还展示了 SCE-Depth 对其他宽视场数据模态（如鱼眼与全景图像）的泛化能力。代码见 https://github.com/ZhuYi2000/SCE-Depth。
英文原文摘要 1521 字符
Accurate depth estimation in wide field is highly desired in applications of autonomous driving, robot vision and drone controls. Biological compound eyes inspire wide Field of View (FOV) depth estimation, yet their artificial implementations face the challenge of modality misalignment. Specifically, the spherical imaging data do not align well with planar neural networks, diminishing the learning efficiency. Herein, we propose SCE-Depth, a bio-inspired framework for spherical compound eye depth estimation, which processes spherical images natively on a HEALPix grid using a spherical neural network. This approach achieves a unified 180deg FOV while avoiding the errors typically introduced by modality conversion. Additionally, we identify a depth-sensitive gradient feature from the overlapping FOVs of adjacent ommatidia. To exploit it, we introduce a spherical Sobel operator called the Spherical Gradient Feature Extractor (SGFE) and a corresponding Spherical Gradient Loss (SGL), which jointly extract gradient features on the HEALPix grid, enabling gradient-aware depth prediction. Extensive benchmark experiments demonstrate that these strategies enable SCE-Depth to substantially reduce depth estimation error compared to fisheye-based baselines, with particularly large improvements in peripheral accuracy. We also demonstrate the generalization capability of SCE-Depth to other wide FOV data modalities, such as fisheye and panoramic imagery. Code is available at https://github.com/ZhuYi2000/SCE-Depth.