# MGNet: Monocular Geometric Scene Understanding for Autonomous Driving

arXiv: https://arxiv.org/abs/2206.13199 · HTML: https://mlsanity.com/paper/2206.13199/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 68 of its 85 references that are in the map.
- First posted on arXiv 27 Jun 2022.

## Builds on (most cited first, 30 of 68)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [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)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [3D Packing for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/1905.02693/) (2019)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Sparsity Invariant CNNs](https://mlsanity.com/paper/1708.06500/) (2017)
- [Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation](https://mlsanity.com/paper/2003.07853/) (2020)
- [SOLO: Segmenting Objects by Locations](https://mlsanity.com/paper/1912.04488/) (2019)
- [PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing](https://mlsanity.com/paper/1805.04409/) (2018)
- [DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution](https://mlsanity.com/paper/2006.02334/) (2020)
- [Hierarchical Multi-Scale Attention for Semantic Segmentation](https://mlsanity.com/paper/2005.10821/) (2020)

## Built on by (most cited first, 27 of 27)

- [PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation](https://mlsanity.com/paper/2406.13378/) (2024)
- [TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection](https://mlsanity.com/paper/2403.08108/) (2024)
- [DepthMaster: Taming Diffusion Models for Monocular Depth Estimation](https://mlsanity.com/paper/2501.02576/) (2025)
- [ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation](https://mlsanity.com/paper/2407.08187/) (2024)
- [The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation](https://mlsanity.com/paper/2307.15061/) (2023)
- [SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images](https://mlsanity.com/paper/2403.10662/) (2024)
- [JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes](https://mlsanity.com/paper/2207.07895/) (2022)
- [Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving](https://mlsanity.com/paper/2309.04422/) (2023)
- [Towards Deeply Unified Depth-aware Panoptic Segmentation with Bi-directional Guidance Learning](https://mlsanity.com/paper/2307.14786/) (2023)
- [Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weather](https://mlsanity.com/paper/2505.12199/) (2025)
- [EC-Depth: Exploring the consistency of self-supervised monocular depth estimation in challenging scenes](https://mlsanity.com/paper/2310.08044/) (2023)
- [Panoptic Perception for Autonomous Driving: A Survey](https://mlsanity.com/paper/2408.15388/) (2024)
- [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025)
- [Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues](https://mlsanity.com/paper/2505.17358/) (2025)
- [M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception](https://mlsanity.com/paper/2510.17363/) (2025)
- [PanDepth: Joint Panoptic Segmentation and Depth Completion](https://mlsanity.com/paper/2212.14180/) (2022)
- [A Dynamic Feature Interaction Framework for Multi-task Visual Perception](https://mlsanity.com/paper/2306.05061/) (2023)
- [RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation](https://mlsanity.com/paper/2305.01255/) (2023)
- [CRF360D: Monocular 360 Depth Estimation via Spherical Fully-Connected CRFs](https://mlsanity.com/paper/2405.11564/) (2024)
- [FusionSAM: Visual Multi-Modal Learning with Segment Anything](https://mlsanity.com/paper/2408.13980/) (2024)
- [Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attacks](https://mlsanity.com/paper/2512.24111/) (2025)
- [MGNiceNet: Unified Monocular Geometric Scene Understanding](https://mlsanity.com/paper/2411.11466/) (2024)
- [Depth as Points: Center Point-based Depth Estimation](https://mlsanity.com/paper/2504.18773/) (2025)
- [LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment](https://mlsanity.com/paper/2505.00980/) (2025)
- [VGLD: Visually-Guided Linguistic Disambiguation for Monocular Depth Scale Recovery](https://mlsanity.com/paper/2505.02704/) (2025)
- [BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World](https://mlsanity.com/paper/2505.16154/) (2025)
- [LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction](https://mlsanity.com/paper/2609.25803/) (2026)

## Abstract (arXiv)

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth estimation. Panoptic segmentation captures the full scene not only semantically, but also on an instance basis. Self-supervised monocular depth estimation uses geometric constraints derived from the camera measurement model in order to measure depth from monocular video sequences only. To the best of our knowledge, we are the first to propose the combination of these two tasks in one single model. Our model is designed with focus on low latency to provide fast inference in real-time on a single consumer-grade GPU. During deployment, our model produces dense 3D point clouds with instance aware semantic labels from single high-resolution camera images. We evaluate our model on two popular autonomous driving benchmarks, i.e., Cityscapes and KITTI, and show competitive performance among other real-time capable methods. Source code is available at https://github.com/markusschoen/MGNet.