mlsanityData to 14 Oct 2026

Soiling detection for Advanced Driver Assistance Systems

arXiv 2511.09740 ↗First posted 12 Nov 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Soiling detection for automotive cameras is a crucial part of advanced driver assistance systems to make them more robust to external conditions like weather, dust, etc. In this paper, we regard the soiling detection as a semantic segmentation problem. We provide a comprehensive comparison of popular segmentation methods and show their superiority in performance while comparing them to tile-level classification approaches. Moreover, we present an extensive analysis of the Woodscape dataset showing that the original dataset contains a data-leakage and imprecise annotations. To address these problems, we create a new data subset, which, despite being much smaller, provides enough information for the segmentation method to reach comparable results in a much shorter time. All our codes and dataset splits are available at https://github.com/filipberanek/woodscape_revision.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 12 Nov 2025.

Builds on

19 of 32 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  6. 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
  7. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 403
  8. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 214
  9. 2018Pyramid Attention Network for Semantic Segmentationcited by 149
  10. 2019WoodScape: A multi-task, multi-camera fisheye dataset for autonomous drivingcited by 144
  11. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  12. 2023DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attentioncited by 91
7 more
  1. 2019UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environmentscited by 84
  2. 2019I Can See Clearly Now : Image Restoration via De-Rainingcited by 23
  3. 2019Robust Semantic Segmentation in Adverse Weather Conditions by means of Sensor Data Fusioncited by 18
  4. 2020TiledSoilingNet: Tile-level Soiling Detection on Automotive Surround-view Cameras Using Coverage Metriccited by 17
  5. 2019SoilingNet: Soiling Detection on Automotive Surround-View Camerascited by 14
  6. 2019Multi-Task Learning for Automotive Foggy Scene Understanding via Domain Adaptation to an Illumination-Invariant Representationcited by 5
  7. 2021Ensemble-based Semi-supervised Learning to Improve Noisy Soiling Annotations in Autonomous Drivingcited by 2

Built on by

Not cited yet.