3D Cloud reconstruction through geospatially-aware Masked Autoencoders
- URL: http://arxiv.org/abs/2501.02035v1
- Date: Fri, 03 Jan 2025 12:26:04 GMT
- Title: 3D Cloud reconstruction through geospatially-aware Masked Autoencoders
- Authors: Stella Girtsou, Emiliano Diaz Salas-Porras, Lilli Freischem, Joppe Massant, Kyriaki-Margarita Bintsi, Guiseppe Castiglione, William Jones, Michael Eisinger, Emmanuel Johnson, Anna Jungbluth,
- Abstract summary: This study leverages geostationary imagery from MSG/SEVIRI and radar reflectivity measurements of cloud profiles from CloudSat/CPR to reconstruct 3D cloud structures.
We first apply self-supervised learning (SSL) methods-Masked Autoencoders (MAE) and geospatially-aware SatMAE on unlabelled MSG images, and then fine-tune our models on matched image-profile pairs.
- Score: 1.4124182346539256
- License:
- Abstract: Clouds play a key role in Earth's radiation balance with complex effects that introduce large uncertainties into climate models. Real-time 3D cloud data is essential for improving climate predictions. This study leverages geostationary imagery from MSG/SEVIRI and radar reflectivity measurements of cloud profiles from CloudSat/CPR to reconstruct 3D cloud structures. We first apply self-supervised learning (SSL) methods-Masked Autoencoders (MAE) and geospatially-aware SatMAE on unlabelled MSG images, and then fine-tune our models on matched image-profile pairs. Our approach outperforms state-of-the-art methods like U-Nets, and our geospatial encoding further improves prediction results, demonstrating the potential of SSL for cloud reconstruction.
Related papers
- Removing cloud shadows from ground-based solar imagery [0.33748750222488655]
We propose a new method to remove cloud shadows, based on a U-Net architecture, and compare classical supervision with conditional GAN.
We evaluate our method on two different imaging modalities, using both real images and a new dataset of synthetic clouds.
arXiv Detail & Related papers (2024-07-18T10:38:24Z) - Few-shot point cloud reconstruction and denoising via learned Guassian splats renderings and fine-tuned diffusion features [52.62053703535824]
We propose a method to reconstruct point clouds from few images and to denoise point clouds from their rendering.
To improve reconstruction in constraint settings, we regularize the training of a differentiable with hybrid surface and appearance.
We demonstrate how these learned filters can be used to remove point cloud noise coming without 3D supervision.
arXiv Detail & Related papers (2024-04-01T13:38:16Z) - HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation [106.09886920774002]
We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network.
Our method achieves consistent improvements over the baseline trained from scratch and significantly out- performs the existing schemes.
arXiv Detail & Related papers (2024-03-18T14:18:08Z) - CLiSA: A Hierarchical Hybrid Transformer Model using Orthogonal Cross
Attention for Satellite Image Cloud Segmentation [5.178465447325005]
Deep learning algorithms have emerged as promising approach to solve image segmentation problems.
In this paper, we introduce a deep-learning model for effective cloud mask generation named CLiSA - Cloud segmentation via Lipschitz Stable Attention network.
We demonstrate both qualitative and quantitative outcomes for multiple satellite image datasets including Landsat-8, Sentinel-2, and Cartosat-2s.
arXiv Detail & Related papers (2023-11-29T09:31:31Z) - IceCloudNet: Cirrus and mixed-phase cloud prediction from SEVIRI input
learned from sparse supervision [26.970640961908032]
Ice particles play a crucial role in the climate system. Yet they remain a source of great uncertainty in climate models and future climate projections.
In this work, we create a new observational constraint of regime-dependent ice-physical properties at geostationary satellite instruments and the quality of active satellite retrievals.
arXiv Detail & Related papers (2023-10-05T12:24:25Z) - Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models [97.58685709663287]
generative pre-training can boost the performance of fundamental models in 2D vision.
In 3D vision, the over-reliance on Transformer-based backbones and the unordered nature of point clouds have restricted the further development of generative pre-training.
We propose a novel 3D-to-2D generative pre-training method that is adaptable to any point cloud model.
arXiv Detail & Related papers (2023-07-27T16:07:03Z) - Exploring the Application of Large-scale Pre-trained Models on Adverse
Weather Removal [97.53040662243768]
We propose a CLIP embedding module to make the network handle different weather conditions adaptively.
This module integrates the sample specific weather prior extracted by CLIP image encoder together with the distribution specific information learned by a set of parameters.
arXiv Detail & Related papers (2023-06-15T10:06:13Z) - MM811 Project Report: Cloud Detection and Removal in Satellite Images [0.0]
We aim to address cloud removal from satellite images using AttentionGAN.
We compare our results by reproducing the results obtained using traditional GANs and auto-encoders.
The outcome of this project can be used to develop applications that require cloud-free satellite images.
arXiv Detail & Related papers (2022-12-21T21:14:35Z) - 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) - Deep Learning Based Cloud Cover Parameterization for ICON [55.49957005291674]
We train NN based cloud cover parameterizations with coarse-grained data based on realistic regional and global ICON simulations.
Globally trained NNs can reproduce sub-grid scale cloud cover of the regional simulation.
We identify an overemphasis on specific humidity and cloud ice as the reason why our column-based NN cannot perfectly generalize from the global to the regional coarse-grained data.
arXiv Detail & Related papers (2021-12-21T16:10:45Z)
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.