OneOcc：基于单个全景相机的腿足机器人语义占用预测
OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera
针对腿足/人形机器人平台，提出仅用单个全景相机进行360°语义占用预测的框架，其双投影融合、双网格体素化和步态位移补偿模块可被复用于其他存在剧烈抖动的移动平台的全景3D感知任务。
原文依据 We present OneOcc, a vision-only panoramic SSC framework tailored to severe body jitter and 360deg continuity.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论鲁棒的3D语义占用对于腿足和人形机器人至关重要，然而大多数语义场景补全（SSC）系统是为配备前向传感器的轮式平台设计的。我们提出OneOcc，一个仅依赖视觉的全景SSC框架，专门针对严重的机体抖动和360°连续性。OneOcc集成了四个互补模块：（i）双投影融合（DP-ER），联合利用原始环形全景图及其等距柱状展开图，在保持真实360°连续性的同时实现网格对齐的特征提取和接缝感知上下文；（ii）双网格体素化（BGV），在笛卡尔和极坐标/柱面体素空间中进行推理，以减少离散化偏差并更好地与全景几何对齐，产生更清晰的自由/占用边界；（iii）一个带有分层AMoE-3D融合的轻量级解码器，动态地将多尺度3D特征路由到专门的专家，改善长程上下文和遮挡处理；（iv）一个即插即用的步态位移补偿（GDC）模块，从步态中学习特征级运动校正，无需额外传感器即可稳定表示。我们还发布了两个全景占用基准：QuadOcc（真实四足机器人，第一人称360°）和Human360Occ（H3O）（CARLA人类自我中心360°，包含RGB/深度/语义占用以及标准化的城市内/跨城市划分）。OneOcc取得了新的SOTA：在QuadOcc上，它超越了强大的视觉基线甚至流行的激光雷达方法，在H3O上，城市内提升了+3.83 mIoU，跨城市提升了+8.08。这些模块轻量级，能够为腿足和人形机器人实现可部署的全环绕语义感知。
英文原文摘要 1647 字符
Robust 3D semantic occupancy is essential for legged and humanoid robots, yet most Semantic Scene Completion (SSC) systems are built for wheeled platforms with forward-facing sensors. We present OneOcc, a vision-only panoramic SSC framework tailored to severe body jitter and 360deg continuity. OneOcc integrates four complementary modules: (i) Dual-Projection fusion (DP-ER), which jointly exploits the raw annular panorama and its equirectangular unfolding to preserve true 360deg continuity while enabling grid-aligned feature extraction and seam-aware context; (ii) Bi-Grid Voxelization (BGV), which reasons in Cartesian and polar/cylindrical voxel spaces to reduce discretization bias and better align with panoramic geometry, yielding sharper free/occupied boundaries; (iii) a lightweight decoder with Hierarchical AMoE-3D fusion that dynamically routes multi-scale 3D features to specialized experts, improving long-range context and occlusion handling; and (iv) a plug-and-play Gait Displacement Compensation (GDC) module that learns feature-level motion correction from gait, stabilizing representations without extra sensors. We also release two panoramic occupancy benchmarks: QuadOcc (real quadruped, first-person 360deg) and Human360Occ (H3O) (CARLA human-ego 360deg with RGB/Depth/semantic-occupancy and standardized within-/cross-city splits). OneOcc sets new SOTA: on QuadOcc it exceeds strong vision baselines and even popular LiDAR methods, and on H3O it improves within-city by +3.83 mIoU and cross-city by +8.08. The modules are lightweight, enabling deployable full-surround semantic perception for legged and humanoid robots.