mlsanityData to 7 Oct 2026

OccTransformer: Improving BEVFormer for 3D camera-only occupancy prediction

arXiv 2402.18140 ↗First posted 28 Feb 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

This technical report presents our solution, "occTransformer" for the 3D occupancy prediction track in the autonomous driving challenge at CVPR 2023. Our method builds upon the strong baseline BEVFormer and improves its performance through several simple yet effective techniques. Firstly, we employed data augmentation to increase the diversity of the training data and improve the model's generalization ability. Secondly, we used a strong image backbone to extract more informative features from the input data. Thirdly, we incorporated a 3D unet head to better capture the spatial information of the scene. Fourthly, we added more loss functions to better optimize the model. Additionally, we used an ensemble approach with the occ model BevDet and SurroundOcc to further improve the performance. Most importantly, we integrated 3D detection model StreamPETR to enhance the model's ability to detect objects in the scene. Using these methods, our solution achieved 49.23 miou on the 3D occupancy prediction track in the autonomous driving challenge.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 16 of its 17 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

16 of 17 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  3. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  4. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  5. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  6. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  7. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 614
  8. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  9. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  10. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  11. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  12. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
4 more
  1. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  2. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  3. 2023Scene as Occupancycited by 208
  4. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
  2. 2025OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervisioncited by 16
  3. 2025VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regionscited by 7
  4. 2024Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecastingcited by 6
  5. 2024BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Networkcited by 0
  6. 2026Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Drivingcited by 0