Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
Summary
The paper proposes Geo-Anchored Cloud Removal (GACR), a framework that uses Observation-Anchored Residual Flow and Geo-Contextual Prior Alignment to remove clouds from optical remote sensing images while preserving semantic structures for downstream tasks.
View Cached Full Text
Cached at: 07/06/26, 10:36 AM
Paper page - Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
Source: https://huggingface.co/papers/2607.02471 Published on Jul 2
·
Submitted byhttps://huggingface.co/wzy6055
WZYon Jul 6
Abstract
Geo-Anchored Cloud Removal framework addresses semantic drift in cloud removal by combining physically grounded residual inversion with semantic manifold constraints from vision foundation models.
Cloud removal(CR) is essential for optical remote sensing, serving as a prerequisite for reliable downstream interpretation, such as semantic segmentation and change detection. However, existing CR approaches often prioritize visual realism while overlooking their impact on subsequent analytical tasks, leading tosemantic driftand degraded downstream performance. To address this issue, we propose Geo-AnchoredCloud Removal(GACR), a unified framework that jointly ensures faithful reconstruction and robust interpretability. At its core, GACR incorporatesObservation-Anchored Residual Flow(OAR-Flow), which reformulates CR as a physically groundedresidual inversion process. By anchoring the generative trajectory to the cloudy observation rather than pure noise, OAR-Flow enables fast, stable, and faithful reconstruction. To further preserve semantic structures critical for downstream interpretation, GACR integratesGeo-Contextual Prior Alignment(GCPA) to constrain the reconstruction within asemantic manifoldinduced by aVision Foundation Model(VFM). Consequently, GACR strictly maintains thespatial-semantic integrityof complex landscapes. Extensive experiments across six CR datasets and twelvedownstream tasksdemonstrate that GACR produces superior reconstruction quality while consistently improving downstream task accuracy. The code is available at https://github.com/wzy6055/GACR.
View arXiv pageView PDFGitHub0Add to collection
Get this paper in your agent:
hf papers read 2607\.02471
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.02471 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.02471 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.02471 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
RemoteZero: Geospatial Reasoning with Zero Human Annotations
RemoteZero is a framework that eliminates the need for human-annotated box supervision in geospatial reasoning by leveraging the semantic verification capabilities of multimodal large language models (MLLMs) to enable self-evolving localization from unlabeled remote sensing data.
Geometry-Aware Infrastructure-Anchored Denoiser for UWB Sensing and Work-Zone Reconstruction
This paper presents GAIA, a geometry-aware learning framework for UWB denoising and work-zone reconstruction that couples temporal range modeling with latent anchor-layout estimation. Evaluated on real-world outdoor data, GAIA reduces range MSE by 18.4% and improves polygon IoU by 15.5% over baselines, demonstrating effective boundary-level reconstruction under NLOS conditions.
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
Introduces GARD, a diffusion-based framework that operates in the feature space of a feed-forward 3D reconstructor to jointly recover scene geometry and high-quality imagery from degraded inputs.
The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning
This paper surveys the emerging paradigm of Geospatial Foundation Models (GeoFMs), which are pre-trained on massive geospatial datasets to enable rapid fine-tuning and zero-shot analysis of satellite and aerial imagery. It covers the paradigm shift, model adaptation strategies, and a forward-looking vision of Agentic Geospatial Reasoning using LLMs as orchestrators.
Spatial Support Matters: Geometry-Aware Graph Fusion for Rainfall Field Reconstruction
This paper proposes a geometry-aware multi-support heterogeneous graph neural network for fine-scale rainfall field reconstruction, which fuses observations from point gauges, path-integrated microwave links, and gridded radar/satellite data. The method reduces RMSE by 23.2% over classical interpolation on Singapore data and shows greatest gains when the field is undersampled relative to its spatial correlation length.