mlsanityData to 7 Oct 2026

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

arXiv 2511.03571 ↗First posted 5 Nov 2025cs.RO cs.CV eess.IVcited by 6

Not on the map. Why?

Abstract (arXiv)

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 360deg continuity. OneOcc combines: (i) Dual-Projection fusion (DP-ER) to exploit the annular panorama and its equirectangular unfolding, preserving 360deg 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 360deg) and Human360Occ (H3O) (CARLA human-ego 360deg 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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 95 of its 118 references that are in the map. First posted on arXiv 5 Nov 2025.

Builds on

95 of 118 references.

References · 95

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  8. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  10. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 914
  11. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  12. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
38 more
  1. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  2. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  3. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  4. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 230
  5. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  6. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  7. 2020LMSCNet: Lightweight Multiscale 3D Semantic Completioncited by 187
  8. 2021FAST-LIO2: Fast Direct LiDAR-inertial Odometrycited by 170
  9. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
  10. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 126
  11. 2020SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instancescited by 123
  12. 2020Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentationcited by 112
  13. 2024SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Predictioncited by 94
  14. 2024GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Predictioncited by 83
  15. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  16. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  17. 2024GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Predictioncited by 66
  18. 2023PointOcc: Cylindrical Tri-Perspective View for Point-based 3D Semantic Occupancy Predictioncited by 51
  19. 2024GaussianOcc: Fully Self-supervised and Efficient 3D Occupancy Estimation with Gaussian Splattingcited by 50
  20. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 46
  21. 2024Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillationcited by 43
  22. 2024EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understandingcited by 43
  23. 2022Review on Panoramic Imaging and Its Applications in Scene Understandingcited by 42
  24. 2023Camera-based 3D Semantic Scene Completion with Sparse Guidance Networkcited by 40
  25. 2021Semantic Segmentation-assisted Scene Completion for LiDAR Point Cloudscited by 37
  26. 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 35
  27. 2023SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusioncited by 30
  28. 2024OccMamba: Semantic Occupancy Prediction with State Space Modelscited by 29
  29. 2024OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Drivingcited by 27
  30. 2025EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Samplercited by 26
  31. 2023OVO: Open-Vocabulary Occupancycited by 24
  32. 2023Revisit Human-Scene Interaction via Space Occupancycited by 24
  33. 2025GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flowcited by 24
  34. 2024Let Occ Flow: Self-Supervised 3D Occupancy Flow Predictioncited by 23
  35. 2025One Flight Over the Gap: A Survey from Perspective to Panoramic Visioncited by 23
  36. 2025GaussGym: An open-source real-to-sim framework for learning locomotion from pixelscited by 22
  37. 2025Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perceptioncited by 21
  38. 2024ALOcc: Adaptive Lifting-Based 3D Semantic Occupancy and Cost Volume-Based Flow Predictionscited by 19

50 most cited of 95 All 95 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  2. 2025TGSFormer: Scalable Temporal Gaussian Splatting for Embodied Semantic Scene Completioncited by 2
  3. 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 2
  4. 2026O3N: Omnidirectional Open-Vocabulary Occupancy Prediction for Embodied Intelligent Roboticscited by 1
  5. 2026RobotPan: A 360^circ Surround-View Robotic Vision System for Embodied Perceptioncited by 0
  6. 2026PanOVOcc: Panoramic Embodied Open-Vocabulary Occupancy Mapping with Long-term Spatial Voxel Memorycited by 0