# Fast Scene Understanding for Autonomous Driving

arXiv: https://arxiv.org/abs/1708.02550 · HTML: https://mlsanity.com/paper/1708.02550/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Aug 2017.

## Built on by (most cited first, 14 of 14)

- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2105.07830/) (2021)
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2206.13199/) (2022)
- [Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing](https://mlsanity.com/paper/2203.14448/) (2022)
- [StereoSpike: Depth Learning with a Spiking Neural Network](https://mlsanity.com/paper/2109.13751/) (2021)
- [Contrastive Multi-Task Dense Prediction](https://mlsanity.com/paper/2307.07934/) (2023)
- [RaidaR: A Rich Annotated Image Dataset of Rainy Street Scenes](https://mlsanity.com/paper/2104.04606/) (2021)
- [A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection](https://mlsanity.com/paper/2110.04079/) (2021)
- [RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception](https://mlsanity.com/paper/2407.10876/) (2024)
- [A Survey of Foundation Models for IoT: Taxonomy and Criteria-Based Analysis](https://mlsanity.com/paper/2506.12263/) (2025)
- [Surround-View Cameras based Holistic Visual Perception for Automated Driving](https://mlsanity.com/paper/2206.05542/) (2022)
- [textttAVROBUSTBENCH: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time](https://mlsanity.com/paper/2506.00358/) (2025)
- [Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement](https://mlsanity.com/paper/2402.03557/) (2024)
- [Advancing Complex Wide-Area Scene Understanding with Hierarchical Coresets Selection](https://mlsanity.com/paper/2507.13061/) (2025)

## Abstract (arXiv)

Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this observation and inspired by recent works that tackle multiple tasks with a single integrated architecture, in this paper we present a real-time efficient implementation based on ENet that solves three autonomous driving related tasks at once: semantic scene segmentation, instance segmentation and monocular depth estimation. Our approach builds upon a branched ENet architecture with a shared encoder but different decoder branches for each of the three tasks. The presented method can run at 21 fps at a resolution of 1024x512 on the Cityscapes dataset without sacrificing accuracy compared to running each task separately.