mlsanityData to 7 Oct 2026

WildOcc: A Benchmark for Off-Road 3D Semantic Occupancy Prediction

arXiv 2410.15792 ↗First posted 21 Oct 2024cs.CV cs.AI cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes. Off-road environments are rich in geometric information, therefore it is suitable for 3D semantic occupancy prediction tasks to reconstruct such scenes. However, most of researches concentrate on on-road environments, and few methods are designed for off-road 3D semantic occupancy prediction due to the lack of relevant datasets and benchmarks. In response to this gap, we introduce WildOcc, to our knowledge, the first benchmark to provide dense occupancy annotations for off-road 3D semantic occupancy prediction tasks. A ground truth generation pipeline is proposed in this paper, which employs a coarse-to-fine reconstruction to achieve a more realistic result. Moreover, we introduce a multi-modal 3D semantic occupancy prediction framework, which fuses spatio-temporal information from multi-frame images and point clouds at voxel level. In addition, a cross-modality distillation function is introduced, which transfers geometric knowledge from point clouds to image features.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 26 of its 36 references that are in the map. First posted on arXiv 21 Oct 2024.

Builds on

26 of 36 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  7. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  10. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  11. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  12. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
14 more
  1. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  2. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  3. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  4. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  5. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  6. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  7. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 162
  8. 2020RELLIS-3D Dataset: Data, Benchmarks and Analysiscited by 118
  9. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  10. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  11. 2023SCPNet: Semantic Scene Completion on Point Cloudcited by 80
  12. 2024Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Predictioncited by 46
  13. 2024MonoOcc: Digging into Monocular Semantic Occupancy Predictioncited by 43
  14. 2022ORFD: A Dataset and Benchmark for Off-Road Freespace Detectioncited by 33

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 2.

9 papers.

  1. 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 35
  2. 2025GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attentioncited by 14
  3. 2025Advancing Off-Road Autonomous Driving: The Large-Scale ORAD-3D Dataset and Comprehensive Benchmarkscited by 8
  4. 2025OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Cameracited by 6
  5. 2025Event-aided Semantic Scene Completioncited by 3
  6. 2025Out-of-Distribution Semantic Occupancy Predictioncited by 2
  7. 2026Panoramic Multimodal Semantic Occupancy Prediction for Quadruped Robotscited by 2
  8. 2025MobileOcc: A Human-Aware Semantic Occupancy Dataset for Mobile Robotscited by 1
  9. 2026Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AIcited by 1