mlsanityData to 14 Oct 2026

Co-SemDepth: Fast Joint Semantic Segmentation and Depth Estimation on Aerial Images

arXiv 2503.17982 ↗First posted 23 Mar 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Understanding the geometric and semantic properties of the scene is crucial in autonomous navigation and particularly challenging in the case of Unmanned Aerial Vehicle (UAV) navigation. Such information may be by obtained by estimating depth and semantic segmentation maps of the surrounding environment and for their practical use in autonomous navigation, the procedure must be performed as close to real-time as possible. In this paper, we leverage monocular cameras on aerial robots to predict depth and semantic maps in low-altitude unstructured environments. We propose a joint deep-learning architecture that can perform the two tasks accurately and rapidly, and validate its effectiveness on MidAir and Aeroscapes benchmark datasets. Our joint-architecture proves to be competitive or superior to the other single and joint architecture methods while performing its task fast predicting 20.2 FPS on a single NVIDIA quadro p5000 GPU and it has a low memory footprint. All codes for training and prediction can be found on this link: https://github.com/Malga-Vision/Co-SemDepth

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 38 of its 67 references that are in the map. First posted on arXiv 23 Mar 2025.

Builds on

38 of 67 references.

References · 38

  1. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  4. 2016Pyramid Scene Parsing Networkcited by 2,479
  5. 2021Vision Transformers for Dense Predictioncited by 1,803
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  7. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  8. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  9. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  10. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  11. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  12. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
26 more
  1. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 403
  2. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  3. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  4. 2020Robust Consistent Video Depth Estimationcited by 188
  5. 2017Understanding Convolution for Semantic Segmentationcited by 168
  6. 2017A Survey of Structure from Motioncited by 158
  7. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  8. 2018Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videoscited by 155
  9. 2019Domain-invariant Stereo Matching Networkscited by 109
  10. 2018Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Videocited by 78
  11. 2020Temporally Distributed Networks for Fast Video Semantic Segmentationcited by 77
  12. 2020Don't Forget The Past: Recurrent Depth Estimation from Monocular Videocited by 71
  13. 2020Efficient Semantic Video Segmentation with Per-frame Inferencecited by 63
  14. 2019Exploiting temporal consistency for real-time video depth estimationcited by 61
  15. 20244M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalitiescited by 52
  16. 2018Dynamic Video Segmentation Networkcited by 51
  17. 2018Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotationscited by 51
  18. 2018Joint Learning of Motion Estimation and Segmentation for Cardiac MR Image Sequencescited by 47
  19. 2016Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networkscited by 36
  20. 2021SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular imagescited by 33
  21. 2024RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptionscited by 21
  22. 2019Efficient Video Semantic Segmentation with Labels Propagation and Refinementcited by 18
  23. 2021GCNDepth: Self-supervised Monocular Depth Estimation based on Graph Convolutional Networkcited by 12
  24. 2016Exploiting Depth from Single Monocular Images for Object Detection and Semantic Segmentationcited by 10
  25. 2018Driving Scene Perception Network: Real-time Joint Detection, Depth Estimation and Semantic Segmentationcited by 10
  26. 2023Self-supervised Semantic Segmentation: Consistency over Transformationcited by 5

Built on by

Not cited yet.