Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources

• URL: http://arxiv.org/abs/2510.03006v1
• Date: Fri, 03 Oct 2025 13:51:35 GMT
• Title: Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources
• Authors: Sara Mobsite, Renaud Hostache, Laure Berti Equille, Emmanuel Roux, Joris Guerin,
• Abstract summary: Supervised deep learning for land cover semantic segmentation (LCS) relies on labeled satellite data.<n>Most existing Sentinel-2 datasets are cloud-free, which limits their usefulness in tropical regions where clouds are common.<n>We develop a cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar data can fill in the gaps caused by cloud-obstructed optical imagery.
• Score: 1.5052861873036498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Supervised deep learning for land cover semantic segmentation (LCS) relies on labeled satellite data. However, most existing Sentinel-2 datasets are cloud-free, which limits their usefulness in tropical regions where clouds are common. To properly evaluate the extent of this problem, we developed a cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar data can fill in the gaps caused by cloud-obstructed optical imagery. We also tackle the issue of losing spatial and/or spectral details during encoder downsampling in deep networks. To mitigate this loss, we propose a lightweight method that injects Normalized Difference Indices (NDIs) into the final decoding layers, enabling the model to retain key spatial features with minimal additional computation. Injecting NDIs enhanced land cover segmentation performance on the DFC2020 dataset, yielding improvements of 1.99% for U-Net and 2.78% for DeepLabV3 on cloud-free imagery. Under cloud-covered conditions, incorporating Sentinel-1 data led to significant performance gains across all models compared to using optical data alone, highlighting the effectiveness of radar-optical fusion in challenging atmospheric scenarios.

Related papers

• CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understanding [4.405830705915443]
  Cloudless analysis is often performed where cloudy images are excluded from machine learning datasets and methods.<n>Cloud robust methods can be achieved by combining optical data with radar, a modality unaffected by clouds.<n>We show that state-of-the-art methods trained on combined clear-sky optical and radar imagery suffer performance drops of 23-33 percentage points when evaluated on cloudy images.
  arXiv  Detail & Related papers  (2026-02-13T06:24:55Z)
• PGCS: Physical Law embedded Generative Cloud Synthesis in Remote Sensing Images [9.655563155560658]
  Physical law embedded generative cloud synthesis method (PGCS) is proposed to generate diverse realistic cloud images to enhance real data. Two cloud correction methods are developed from PGCS and exhibits a superior performance compared to state-of-the-art methods in the cloud correction task.
  arXiv  Detail & Related papers  (2024-10-22T12:36:03Z)
• Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning [49.91297276176978]
  We propose a novel intrinsic textbfPointGST (textbfGraph textbfSpectral textbfTuning) method for point cloud.<n>Point GST freezes the pre-trained model and introduces a lightweight, trainable Point Cloud Spectral Adapter (PCSA) for fine-tuning parameters in the spectral domain.<n>Experiments on challenging point cloud datasets across various tasks demonstrate that Point GST not only outperforms its fully fine-tuning counterpart but also significantly reduces trainable parameters.
  arXiv  Detail & Related papers  (2024-10-10T17:00:04Z)
• ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors [52.72867922938023]
  3D point clouds directly collected from objects through sensors are often incomplete due to self-occlusion.<n>We propose a test-time framework for completing partial point clouds across unseen categories without any requirement for training.
  arXiv  Detail & Related papers  (2024-04-10T08:02:17Z)
• IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images [55.40601468843028]
  We present an iterative diffusion process for cloud removal (IDF-CR) IDF-CR is divided into two-stage models that address pixel space and latent space. In the latent space stage, the diffusion model transforms low-quality cloud removal into high-quality clean output.
  arXiv  Detail & Related papers  (2024-03-18T15:23:48Z)
• Creating and Leveraging a Synthetic Dataset of Cloud Optical Thickness Measures for Cloud Detection in MSI [3.4764766275808583]
  Cloud formations often obscure optical satellite-based monitoring of the Earth's surface. We propose a novel synthetic dataset for cloud optical thickness estimation. We leverage for obtaining reliable and versatile cloud masks on real data.
  arXiv  Detail & Related papers  (2023-11-23T14:28:28Z)
• Boosting Point Clouds Rendering via Radiance Mapping [49.24193509772339]
  We focus on boosting the image quality of point clouds rendering with a compact model design. We simplify the NeRF representation to a spatial mapping function which only requires single evaluation per pixel. Our method achieves the state-of-the-art rendering on point clouds, outperforming prior works by notable margins.
  arXiv  Detail & Related papers  (2022-10-27T01:25:57Z)
• A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion [69.32451612060214]
  Real-scanned 3D point clouds are often incomplete, and it is important to recover complete point clouds for downstream applications. Most existing point cloud completion methods use Chamfer Distance (CD) loss for training. We propose a novel Point Diffusion-Refinement (PDR) paradigm for point cloud completion.
  arXiv  Detail & Related papers  (2021-12-07T06:59:06Z)
• A Recommender System-Inspired Cloud Data Filling Scheme for Satellite-based Coastal Observation [0.0]
  This study is inspired by the success of data imputation methods in recommender systems that are designed for online shopping. A numerical experiment was designed and conducted for a LandSat dataset with a range of synthetic cloud covers. The recommender system-inspired matrix factorization algorithm called Funk-SVD showed superior performance in computational accuracy and efficiency.
  arXiv  Detail & Related papers  (2021-11-27T18:26:11Z)
• Sentinel-1 and Sentinel-2 Spatio-Temporal Data Fusion for Clouds Removal [51.9654625216266]
  A novel method for clouds-corrupted optical image restoration has been presented and developed based on a joint data fusion paradigm. It is worth highlighting that the Sentinel code and the dataset have been implemented from scratch and made available to interested research for further analysis and investigation.
  arXiv  Detail & Related papers  (2021-06-23T08:15:01Z)
• Multi-Sensor Data Fusion for Cloud Removal in Global and All-Season Sentinel-2 Imagery [15.459106705735376]
  The majority of optical observations acquired via spaceborne earth imagery are affected by clouds. We target the challenge of generalization by curating a large novel data set for training new cloud removal approaches. Based on the observation that cloud coverage varies widely between clear skies and absolute coverage, we propose a novel model that can deal with either extremes.
  arXiv  Detail & Related papers  (2020-09-16T13:40:42Z)
• GRNet: Gridding Residual Network for Dense Point Cloud Completion [54.43648460932248]
  Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. We propose a novel Gridding Residual Network (GRNet) for point cloud completion. Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.
  arXiv  Detail & Related papers  (2020-06-06T02:46:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.