Delineate Anything v2: A Global Foundation Model for Field Delineation

• URL: http://arxiv.org/abs/2607.19069v1
• Date: Tue, 21 Jul 2026 12:59:45 GMT
• Title: Delineate Anything v2: A Global Foundation Model for Field Delineation
• Abstract summary: We introduce Delineate Anything v2, a globally scalable foundation model for wide-area field boundary.<n>In this work, we demonstrate the ability to build a framework that surpasses the state-of-the-art benchmark for zero-shot capabilities.
• Score: 2.9595476100051896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate agricultural field boundary delineation at large scale is a foundational task for food security, supply chain transparency, and carbon accounting. While vision foundation models like SAM show remarkable zero-shot capabilities, they frequently fail in geospatial domains due to topological complexity, cropland texturing patterns, and a lack of physical scale awareness. In this work, we introduce Delineate Anything v2, a globally scalable foundation model designed specifically for wide-area field boundary mapping. We construct FBIS-73M, a 73-million-instance multi-resolution dataset spanning 61 countries. To address the pervasive issue of multi-field administrative parcel merging, we introduce a resolution-specific data curation pipeline that leverages topological image-space adaptation to homogenize merged parcels and strengthen weak physical boundaries. Furthermore, we establish a novel, manually curated evaluation benchmark covering 100 countries to assess independent zero-shot generalization. Our results show that Delineate Anything v2 surpasses the current state-of-the-art, including the Delineate Anything framework, by 0.284 mAP@0.5 (+103.3% relative gain), while maintaining execution speeds suitable for rapid national- and global-scale deployment, as demonstrated by nationwide mapping of Ukraine (603,000 km^2) in 5.4 hours on a consumer-grade workstation. Code, pre-trained weights, the FBIS-73M dataset, and ready-to-use national-scale vector boundary products are publicly available at https://github.com/Lavreniuk/Delineate-Anything.

Related papers

• The first global agricultural field boundary map at 10m resolution [23.150413419951388]
  Most global remote-sensing products for agriculture are only available at the pixel level.<n>No openly available, globally consistent map of agricultural field boundaries exists to date.<n>We present the first global field boundary dataset at 10,m resolution for the years 2024 and 2025.
  arXiv  Detail & Related papers  (2026-05-11T15:54:42Z)
• Map2World: Segment Map Conditioned Text to 3D World Generation [64.2098235580955]
  3D world generation is essential for immersive content creation or autonomous driving simulation.<n>Recent advances in 3D world generation have shown promising results; however, these methods are constrained by grid layouts.<n>We introduce a novel framework, Map2World, that first enables 3D world generation conditioned on user-defined segment maps of arbitrary shapes and scales.
  arXiv  Detail & Related papers  (2026-05-01T16:56:49Z)
• PRUE: A Practical Recipe for Field Boundary Segmentation at Scale [50.194423500109025]
  We conduct the first systematic evaluation of segmentation and geospatial foundation models (GFMs) for global field boundary delineation.<n>A U-Net semantic segmentation model outperforms instance-based and GFM alternatives on a suite of performance and deployment metrics.<n>Our approach provides a practical framework for reliable, scalable, and reproducible field boundary delineation across model design, training, and inference.
  arXiv  Detail & Related papers  (2026-03-28T02:47:46Z)
• Breaking the Regional Barrier: Inductive Semantic Topology Learning for Worldwide Air Quality Forecasting [99.4484686548807]
  We propose OmniAir, a semantic topology learning framework tailored for global station-level prediction.<n>Our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks.<n>Experiments show that OmniAir achieves state-of-the-art performance against 18 baselines, maintaining high efficiency and scalability with speeds nearly 10 times faster than existing models.
  arXiv  Detail & Related papers  (2026-01-29T15:58:07Z)
• Geodiffussr: Generative Terrain Texturing with Elevation Fidelity [48.82552523546255]
  We introduce Geodiffussr, a flow-matching pipeline that synthesizes text-guided texture maps.<n>The core mechanism is multi-scale content aggregation (MCA): DEM features are injected into UNet blocks at multiple resolutions to enforce global-to-local elevation consistency.<n>To train and evaluate Geodiffussr, we assemble a globally distributed, biome- and climate-stratified corpus of triplets pairing SRTM-derived DEMs with Sentinel-2 imagery and vision-grounded natural-appearance captions.
  arXiv  Detail & Related papers  (2025-11-28T09:52:44Z)
• Delineate Anything Flow: Fast, Country-Level Field Boundary Detection from Any Source [3.7887942935151493]
  Delineate Anything Flow (DelAnyFlow) is a resolution-agnostic approach for large-scale field boundary mapping.<n>FBIS 22M, the largest dataset of its kind, contains 672,909 multi-resolution image patches (0.25-10m) and 22.9million validated field instances.<n>DelAnyFlow generated a complete field boundary layer for Ukraine (603,000km2) in under six hours on a single workstation.
  arXiv  Detail & Related papers  (2025-11-17T14:30:43Z)
• Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery [0.0]
  We introduce the Field Boundary Instance - 22M dataset (FBIS-22M), a large-scale, multi-resolution instance dataset.<n>We propose Delineate Anything, an instance segmentation model trained on the FBIS-22M dataset.<n>Our proposed model sets a new state-of-the-art, achieving a substantial improvement of 88.5% in mAP@0.5 and 103% in mAP@0.5:0.95 over existing methods.
  arXiv  Detail & Related papers  (2025-04-03T12:37:04Z)
• Recognize Any Regions [55.76437190434433]
  RegionSpot integrates position-aware localization knowledge from a localization foundation model with semantic information from a ViL model.<n>Experiments in open-world object recognition show that our RegionSpot achieves significant performance gain over prior alternatives.
  arXiv  Detail & Related papers  (2023-11-02T16:31:49Z)
• Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery [42.70832378336697]
  High-resolution satellite images can provide abundant, detailed spatial information for land cover classification. Few studies have applied high-resolution images to land cover mapping in detailed categories at large scale. We present a large-scale land cover dataset, Five-Billion-Pixels. It contains more than 5 billion labeled pixels of 150 high-resolution Gaofen-2 (4 m) satellite images.
  arXiv  Detail & Related papers  (2022-09-01T21:00:23Z)
• Jalisco's multiclass land cover analysis and classification using a novel lightweight convnet with real-world multispectral and relief data [51.715517570634994]
  We present our novel lightweight (only 89k parameters) Convolution Neural Network (ConvNet) to make LC classification and analysis. In this work, we combine three real-world open data sources to obtain 13 channels. Our embedded analysis anticipates the limited performance in some classes and gives us the opportunity to group the most similar.
  arXiv  Detail & Related papers  (2022-01-26T14:58:51Z)

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.