mlsanityData to 7 Oct 2026

A Simple Framework for 3D Occupancy Estimation in Autonomous Driving

arXiv 2303.10076 ↗First posted 17 Mar 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The task of estimating 3D occupancy from surrounding-view images is an exciting development in the field of autonomous driving, following the success of Bird's Eye View (BEV) perception. This task provides crucial 3D attributes of the driving environment, enhancing the overall understanding and perception of the surrounding space. In this work, we present a simple framework for 3D occupancy estimation, which is a CNN-based framework designed to reveal several key factors for 3D occupancy estimation, such as network design, optimization, and evaluation. In addition, we explore the relationship between 3D occupancy estimation and other related tasks, such as monocular depth estimation and 3D reconstruction, which could advance the study of 3D perception in autonomous driving. For evaluation, we propose a simple sampling strategy to define the metric for occupancy evaluation, which is flexible for current public datasets. Moreover, we establish the benchmark in terms of the depth estimation metric, where we compare our proposed method with monocular depth estimation methods on the DDAD and Nuscenes datasets and achieve competitive performance. The relevant code will be updated in https://github.com/GANWANSHUI/SimpleOccupancy.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 38 of its 57 references that are in the map. First posted on arXiv 17 Mar 2023.

Builds on

38 of 57 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  9. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  10. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  11. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  12. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
26 more
  1. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  2. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  3. 2018Pyramid Stereo Matching Networkcited by 486
  4. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  5. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  6. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  7. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  8. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  9. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  10. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  11. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 280
  12. 2023OpenOccupancy: A Large Scale Benchmark for Surrounding Semantic Occupancy Perceptioncited by 218
  13. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  14. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  15. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  16. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  17. 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
  18. 2022Vision-Centric BEV Perception: A Surveycited by 126
  19. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  20. 20213D Semantic Scene Completion: a Surveycited by 74
  21. 2023Behind the Scenes: Density Fields for Single View Reconstructioncited by 63
  22. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 61
  23. 2022SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fieldscited by 49
  24. 2022V4d: voxel for 4d novel view synthesiscited by 42
  25. 2021Full Surround Monodepth from Multiple Camerascited by 41
  26. 2022LOPR: Latent Occupancy PRediction using Generative Modelscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2023Camera-based 3D Semantic Scene Completion with Sparse Guidance Networkcited by 40
  2. 2023OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environmentscited by 39
  3. 2024Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunitiescited by 24
  4. 2024BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Networkcited by 0