Robust 3D semantic occupancy is crucial for legged/humanoid robots, yet most semantic scene completion (SSC) systems target wheeled platforms with forward-facing sensors. We present OneOcc, a vision-only panoramic SSC framework designed for gait-introduced body jitter and 360{\deg} continuity. OneOcc combines: (i) Dual-Projection fusion (DP-ER) to exploit the annular panorama and its equirectangular unfolding, preserving 360{\deg} continuity and grid alignment; (ii) Bi-Grid Voxelization (BGV) to reason in Cartesian and cylindrical-polar spaces, reducing discretization bias and sharpening free/occupied boundaries; (iii) a lightweight decoder with Hierarchical AMoE-3D for dynamic multi-scale fusion and better long-range/occlusion reasoning; and (iv) plug-and-play Gait Displacement Compensation (GDC) learning feature-level motion correction without extra sensors. We also release two panoramic occupancy benchmarks: QuadOcc (real quadruped, first-person 360{\deg}) and Human360Occ (H3O) (CARLA human-ego 360{\deg} with RGB, Depth, semantic occupancy; standardized within-/cross-city splits). OneOcc sets new state-of-the-art (SOTA): on QuadOcc it beats strong vision baselines and popular LiDAR ones; on H3O it gains +3.83 mIoU (within-city) and +8.08 (cross-city). Modules are lightweight, enabling deployable full-surround perception for legged/humanoid robots. Datasets and code will be publicly available at https://github.com/MasterHow/OneOcc.

翻译：鲁棒的三维语义占据对于腿式/人形机器人至关重要，然而大多数语义场景补全（SSC）系统面向配备前向传感器的轮式平台。我们提出了OneOcc，一个专为步态引发的机体抖动和360度连续性设计的纯视觉全景SSC框架。OneOcc融合了：（i）双投影融合（DP-ER），利用环形全景及其等距柱面展开，保持360度连续性和网格对齐；（ii）双网格体素化（BGV），在笛卡尔空间和柱极坐标空间中进行推理，减少离散化偏差并锐化自由/占据边界；（iii）配备分层AMoE-3D的轻量级解码器，实现动态多尺度融合和更优的长距离/遮挡推理；（iv）即插即用的步态位移补偿（GDC），无需额外传感器即可学习特征级运动校正。我们还发布了两项全景占据基准：QuadOcc（真实四足机器人，第一人称360度）和Human360Occ（H3O）（CARLA仿真人类视角360度，包含RGB、深度、语义占据；采用标准化的城内/跨城划分）。OneOcc确立了新的最先进（SOTA）性能：在QuadOcc上超越了强大的视觉基线和流行的激光雷达方法；在H3O上分别实现了+3.83 mIoU（城内）和+8.08（跨城）的提升。各模块均轻量化，可为腿式/人形机器人实现可部署的全向感知。数据集与代码将公开于 https://github.com/MasterHow/OneOcc。