# Deformable Convolution Based Road Scene Semantic Segmentation of Fisheye Images in Autonomous Driving

arXiv: https://arxiv.org/abs/2407.16647 · HTML: https://mlsanity.com/paper/2407.16647/

## Key facts

- Cited by 2 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 23 Jul 2024.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Spherical CNNs](https://mlsanity.com/paper/1801.10130/) (2018)
- [ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation](https://mlsanity.com/paper/1606.02147/) (2016)
- [WoodScape: A multi-task, multi-camera fisheye dataset for autonomous driving](https://mlsanity.com/paper/1905.01489/) (2019)
- [OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving](https://mlsanity.com/paper/2102.07448/) (2021)
- [Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras](https://mlsanity.com/paper/1801.00708/) (2018)
- [SynWoodScape: Synthetic Surround-view Fisheye Camera Dataset for Autonomous Driving](https://mlsanity.com/paper/2203.05056/) (2022)
- [Universal Semantic Segmentation for Fisheye Urban Driving Images](https://mlsanity.com/paper/2002.03736/) (2020)
- [FusionNet: A deep fully residual convolutional neural network for image segmentation in connectomics](https://mlsanity.com/paper/1612.05360/) (2016)
- [CubemapSLAM: A Piecewise-Pinhole Monocular Fisheye SLAM System](https://mlsanity.com/paper/1811.12633/) (2018)
- [Mapped Convolutions](https://mlsanity.com/paper/1906.11096/) (2019)
- [Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space](https://mlsanity.com/paper/2206.11895/) (2022)
- [Woodscape Fisheye Semantic Segmentation for Autonomous Driving -- CVPR 2021 OmniCV Workshop Challenge](https://mlsanity.com/paper/2107.08246/) (2021)

## Built on by (most cited first, 2 of 2)

- [FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception](https://mlsanity.com/paper/2511.17210/) (2025)
- [FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters](https://mlsanity.com/paper/2610.02799/) (2026)

## Abstract (arXiv)

This study investigates the effectiveness of modern Deformable Convolutional Neural Networks (DCNNs) for semantic segmentation tasks, particularly in autonomous driving scenarios with fisheye images. These images, providing a wide field of view, pose unique challenges for extracting spatial and geometric information due to dynamic changes in object attributes. Our experiments focus on segmenting the WoodScape fisheye image dataset into ten distinct classes, assessing the Deformable Networks' ability to capture intricate spatial relationships and improve segmentation accuracy. Additionally, we explore different loss functions to address class imbalance issues and compare the performance of conventional CNN architectures with Deformable Convolution-based CNNs, including Vanilla U-Net and Residual U-Net architectures. The significant improvement in mIoU score resulting from integrating Deformable CNNs demonstrates their effectiveness in handling the geometric distortions present in fisheye imagery, exceeding the performance of traditional CNN architectures. This underscores the significant role of Deformable convolution in enhancing semantic segmentation performance for fisheye imagery.