RayOcc：通过高斯混合强度进行遮挡感知光线占有率估计
RayOcc: Occlusion-Aware Ray Occupancy Estimation via Gaussian Mixture Intensity
浏览论文内容
中文总结 AI 辅助
研究针对仅相机的3D语义占有率预测中因深度模糊和遮挡带来的挑战，提出RayOcc框架。该框架将光线建模为多标签存在预测，通过估计高斯混合强度及转换为占有率概率，初始化高斯基元进行语义占有率预测，在nuScenes基准测试中取得最优成绩。
中文摘要 AI 辅助
仅使用相机的3D语义占有率预测旨在从多视图图像推断体素级场景语义，但由于深度模糊和遮挡，这一任务仍具有根本挑战性。沿单条相机光线，多个空间分离的表面可能共存，使占有率本质上成为多标签存在问题而非单深度估计任务。大多数现有方法倾向于每条光线的单个主导深度假设，限制了其在复杂遮挡下对体积场景建模的能力。为解决此限制问题，我们引入RayOcc，这是一个遮挡感知光线占有率框架，将光线建模重新表述为多标签存在预测。RayOcc不是预测分类深度分布，而是沿每条光线估计非归一化高斯混合强度，并通过泊松事件公式将其转换为区间占有率概率，允许多个占用假设共存而无需在深度上强制执行相互竞争。预测的混合成分被解释为占用假设，以初始化稀疏3D高斯基元，这些基元经过细化和光栅化以进行语义占有率预测。在nuScenes基准测试上的实验表明，RayOcc在基于高斯的占有率方法中实现了当前最优的总体IoU和mIoU。
英文摘要
Camera-only 3D semantic occupancy prediction aims to infer voxel-wise scene semantics from multi-view images, yet remains fundamentally challenging due to depth ambiguity and occlusion. Along a single camera ray, multiple spatially separated surfaces may coexist, making occupancy inherently a multi-label existence problem rather than a single-depth estimation task. However, most existing approaches favor a single dominant depth hypothesis per ray, limiting their ability to model volumetric scenes under complex occlusion. To address this limitation, we introduce RayOcc, an occlusion-aware ray occupancy framework that reformulates ray modeling as multi-label existence prediction. Instead of predicting a categorical depth distribution, RayOcc estimates a non-normalized Gaussian mixture intensity along each ray and converts it into interval-wise occupancy probabilities via a Poisson event formulation, allowing multiple occupied hypotheses to coexist without enforcing mutual competition across depth. The predicted mixture components are interpreted as occupancy hypotheses to initialize sparse 3D Gaussian primitives, which are refined and rasterized for semantic occupancy prediction. Experiments on the nuScenes benchmark show that RayOcc achieves state-of-the-art overall IoU and mIoU among the compared Gaussian-based occupancy methods.
发表机构
- School of Electrical Engineering, Kookmin University（韩国建国大学电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。
