# SatEdit: Mask-Conditioned Image Editing via VLM-Guided Segment Annotation

arXiv: https://arxiv.org/abs/2607.29367 · HTML: https://mlsanity.com/paper/2607.29367/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [RSEdit: Text-Guided Image Editing for Remote Sensing](https://mlsanity.com/paper/2603.13708/) (2026)
- [TerraDiT-Omega: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive](https://mlsanity.com/paper/2606.31029/) (2026)

## Abstract (arXiv)

Satellite image editing requires spatially precise object-level control, but supervised editing datasets for overhead imagery are costly to build because object masks, semantic labels, and paired edits are rarely available at scale. We introduce SatEdit, a mask-conditioned satellite image editing framework that constructs training supervision from unlabeled imagery. SatEdit proposes object masks with a seg- mentation foundation model, assigns semantic la- bels to sampled segments with a Vision-Language Model, and applies lightweight human verification before generating paired addition and removal exam- ples through mask-guided inpainting. We fine-tune a high-resolution image editing backbone with LoRA on a SODA-A-derived dataset containing 1,014 im- ages and 852 verified object annotations across 91 classes. In controlled comparisons with open- source and proprietary image editing models, SatE- dit achieves the highest aggregate masked-region se- mantic alignment, with a CLIP score of 0.6322 and CLIP delta of 0.0726, while preserving the surround- ing scene qualitatively. These results suggest that VLM-assisted segment annotation is a practical route to data-efficient, spatially controllable satellite image editing.