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

arXiv: https://arxiv.org/abs/2402.18140 · HTML: https://mlsanity.com/paper/2402.18140/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 17 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving](https://mlsanity.com/paper/2304.14365/) (2023)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [Scene as Occupancy](https://mlsanity.com/paper/2306.02851/) (2023)
- [OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.13540/) (2023)

## Built on by (most cited first, 6 of 6)

- [Vision-based 3D occupancy prediction in autonomous driving: a review and outlook](https://mlsanity.com/paper/2405.02595/) (2024)
- [OccVLA: Vision-Language-Action Model with Implicit 3D Occupancy Supervision](https://mlsanity.com/paper/2509.05578/) (2025)
- [VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions](https://mlsanity.com/paper/2507.19188/) (2025)
- [Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting](https://mlsanity.com/paper/2411.14169/) (2024)
- [BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network](https://mlsanity.com/paper/2405.17037/) (2024)
- [Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.21470/) (2026)

## 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.