# FoveaNet: Perspective-aware Urban Scene Parsing

arXiv: https://arxiv.org/abs/1708.02421 · HTML: https://mlsanity.com/paper/1708.02421/

## Key facts

- Cited by 12 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 8 Aug 2017.

## Built on by (most cited first, 12 of 12)

- [Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation](https://mlsanity.com/paper/2107.11264/) (2021)
- [Foveation in the Era of Deep Learning](https://mlsanity.com/paper/2312.01450/) (2023)
- [Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes](https://mlsanity.com/paper/2111.15463/) (2021)
- [CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning](https://mlsanity.com/paper/2512.08135/) (2025)
- [Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection](https://mlsanity.com/paper/2303.14311/) (2023)
- [Perspective Aware Road Obstacle Detection](https://mlsanity.com/paper/2210.01779/) (2022)
- [Semantic Segmentation for Urban-Scene Images](https://mlsanity.com/paper/2110.13813/) (2021)
- [VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2408.03551/) (2024)
- [HM-Net: A Regression Network for Object Center Detection and Tracking on Wide Area Motion Imagery](https://mlsanity.com/paper/2110.09881/) (2021)
- [FBNet: Feature Balance Network for Urban-Scene Segmentation](https://mlsanity.com/paper/2111.03286/) (2021)
- [Domain Adaptive Semantic Segmentation by Optimal Transport](https://mlsanity.com/paper/2303.16435/) (2023)
- [CF-YOLO: Context-Aware Feature Refinement for Camouflaged Industrial Micro-Defect Detection](https://mlsanity.com/paper/2608.28070/) (2026)

## Abstract (arXiv)

Parsing urban scene images benefits many applications, especially self-driving. Most of the current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors. In this work, we propose a new FoveaNet model to fully exploit the perspective geometry of scene images and address the common failures of generic parsing models. FoveaNet estimates the perspective geometry of a scene image through a convolutional network which integrates supportive evidence from contextual objects within the image. Based on the perspective geometry information, FoveaNet "undoes" the camera perspective projection analyzing regions in the space of the actual scene, and thus provides much more reliable parsing results. Furthermore, to effectively address the recognition errors, FoveaNet introduces a new dense CRFs model that takes the perspective geometry as a prior potential. We evaluate FoveaNet on two urban scene parsing datasets, Cityspaces and CamVid, which demonstrates that FoveaNet can outperform all the well-established baselines and provide new state-of-the-art performance.