# Adapting CNNs for Fisheye Cameras without Retraining

arXiv: https://arxiv.org/abs/2404.08187 · HTML: https://mlsanity.com/paper/2404.08187/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 12 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [Learning SO(3) Equivariant Representations with Spherical CNNs](https://mlsanity.com/paper/1711.06721/) (2017)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth](https://mlsanity.com/paper/1904.02028/) (2019)
- [Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation](https://mlsanity.com/paper/2203.01452/) (2022)
- [Kernel Transformer Networks for Compact Spherical Convolution](https://mlsanity.com/paper/1812.03115/) (2018)
- [Generalized Object Detection on Fisheye Cameras for Autonomous Driving: Dataset, Representations and Baseline](https://mlsanity.com/paper/2012.02124/) (2020)
- [Universal Semantic Segmentation for Fisheye Urban Driving Images](https://mlsanity.com/paper/2002.03736/) (2020)
- [Active Convolution: Learning the Shape of Convolution for Image Classification](https://mlsanity.com/paper/1703.09076/) (2017)

## Built on by (most cited first, 3 of 3)

- [Benchmarking Multi-View BEV Object Detection with Mixed Pinhole and Fisheye Cameras](https://mlsanity.com/paper/2603.27818/) (2026)
- [Distortion-Aware PETR for BEV Object Detection with Mixed Pinhole-Fisheye Cameras](https://mlsanity.com/paper/2606.08680/) (2026)
- [Geometry-Aware Fisheye-LiDAR Fusion for Robust 3D Object Detection in Low-Overlap Setups](https://mlsanity.com/paper/2606.08844/) (2026)

## Abstract (arXiv)

The majority of image processing approaches assume images are in or can be rectified to a perspective projection. However, in many applications it is beneficial to use non conventional cameras, such as fisheye cameras, that have a larger field of view (FOV). The issue arises that these large-FOV images can't be rectified to a perspective projection without significant cropping of the original image. To address this issue we propose Rectified Convolutions (RectConv); a new approach for adapting pre-trained convolutional networks to operate with new non-perspective images, without any retraining. Replacing the convolutional layers of the network with RectConv layers allows the network to see both rectified patches and the entire FOV. We demonstrate RectConv adapting multiple pre-trained networks to perform segmentation and detection on fisheye imagery from two publicly available datasets. Our approach requires no additional data or training, and operates directly on the native image as captured from the camera. We believe this work is a step toward adapting the vast resources available for perspective images to operate across a broad range of camera geometries.