# Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Cameras

arXiv: https://arxiv.org/abs/2606.08680 · HTML: https://mlsanity.com/paper/2606.08680/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 30 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://mlsanity.com/paper/2206.15398/) (2022)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth](https://mlsanity.com/paper/1904.02028/) (2019)
- [Polar Parametrization for Vision-based Surround-View 3D Detection](https://mlsanity.com/paper/2206.10965/) (2022)
- [Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges](https://mlsanity.com/paper/2205.13281/) (2022)
- [HEAL-SWIN: A Vision Transformer On The Sphere](https://mlsanity.com/paper/2307.07313/) (2023)
- [F2BEV: Bird's Eye View Generation from Surround-View Fisheye Camera Images for Automated Driving](https://mlsanity.com/paper/2303.03651/) (2023)
- [DarSwin: Distortion Aware Radial Swin Transformer](https://mlsanity.com/paper/2304.09691/) (2023)
- [Convolution kernel adaptation to calibrated fisheye](https://mlsanity.com/paper/2402.01456/) (2024)
- [PolarBEVDet: Exploring Polar Representation for Multi-View 3D Object Detection in Bird's-Eye-View](https://mlsanity.com/paper/2408.16200/) (2024)
- [Adapting CNNs for Fisheye Cameras without Retraining](https://mlsanity.com/paper/2404.08187/) (2024)
- [FisheyeDetNet: 360deg Surround view Fisheye Camera based Object Detection System for Autonomous Driving](https://mlsanity.com/paper/2404.13443/) (2024)
- [Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras](https://mlsanity.com/paper/2603.27818/) (2026)

## Abstract (arXiv)

Fisheye cameras are widely deployed in autonomous driving perception suites for their low cost and full-coverage field of view (FOV), yet their potential remains underleveraged in 3D object detection. Severe radial distortion challenges most BEV detectors by violating the fundamental assumption of uniform sampling. To bridge this gap, we propose Distortion-Aware PETR (DAPETR), a projection-free detector tailored for mixed pinhole-fisheye camera setups. DAPETR incorporates two key learned-adaptive modules: a unified distortion-aware positional embedding that harmonizes positional encodings for image representations with fisheye geometry, and a bidirectional feature-geometry co-modulation module that mutually adapts image features and 3D positional embeddings. In our experiments on a converted KITTI-360 benchmark, we systematically compare our learned adaptive approach against PETR in polar coordinates (PolarPETR). We find that while both methods improve over the baseline, our learned modules achieve superior performance. Crucially, we uncover a negative interaction when combining both strategies, revealing that learned adaptation and explicit geometric reparameterization can conflict. Our final DAPETR model significantly advances the research and benchmark for fisheye BEV detection, providing critical insights into effective distortion-aware 3D perception design other than image rectification.