OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera

TL;DR

OneOcc introduces a novel panoramic semantic occupancy framework for legged robots, combining dual-projection fusion, bi-grid voxelization, and motion correction to achieve state-of-the-art results with lightweight modules.

Contribution

The paper presents a new vision-only panoramic SSC framework tailored for legged robots, including novel fusion, voxelization, and motion correction techniques, along with new benchmarks.

Findings

Sets new state-of-the-art on QuadOcc benchmark.

Achieves +3.83 mIoU improvement on H3O within-city.

Modules are lightweight and suitable for deployment on robots.

Abstract

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 a new state of the art on QuadOcc, outperforming strong vision baselines and remaining competitive with classical LiDAR baselines; 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.