# Quantitative Comparison of Fine-Tuning Techniques for Pretrained Latent Diffusion Models in the Generation of Unseen SAR Images

arXiv: https://arxiv.org/abs/2506.13307 · HTML: https://mlsanity.com/paper/2506.13307/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 16 Jun 2025.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 17 of 17)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2306.11300/) (2023)
- [Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model](https://mlsanity.com/paper/2501.00895/) (2025)
- [MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation](https://mlsanity.com/paper/2405.13570/) (2024)
- [HSIGene: A Foundation Model For Hyperspectral Image Generation](https://mlsanity.com/paper/2409.12470/) (2024)
- [SARChat-Bench-2M: A Multi-Task Vision-Language Benchmark for SAR Image Interpretation](https://mlsanity.com/paper/2502.08168/) (2025)
- [Synthetic Art Generation and DeepFake Detection A Study on Jamini Roy Inspired Dataset](https://mlsanity.com/paper/2503.23226/) (2025)
- [From Spaceborne to Airborne: SAR Image Synthesis Using Foundation Models for Multi-Scale Adaptation](https://mlsanity.com/paper/2505.03844/) (2025)

## Built on by (most cited first, 3 of 3)

- [SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm](https://mlsanity.com/paper/2606.20523/) (2026)
- [The Global-Local loop: what is missing in bridging the gap between geospatial data from numerous communities?](https://mlsanity.com/paper/2603.20305/) (2026)
- [ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution](https://mlsanity.com/paper/2609.02377/) (2026)

## Abstract (arXiv)

We present a framework for adapting a large pretrained latent diffusion model to high-resolution Synthetic Aperture Radar (SAR) image generation. The approach enables controllable synthesis and the creation of rare or out-of-distribution scenes beyond the training set. Rather than training a task-specific small model from scratch, we adapt an open-source text-to-image foundation model to the SAR modality, using its semantic prior to align prompts with SAR imaging physics (side-looking geometry, slant-range projection, and coherent speckle with heavy-tailed statistics). Using a 100k-image SAR dataset, we compare full fine-tuning and parameter-efficient Low-Rank Adaptation (LoRA) across the UNet diffusion backbone, the Variational Autoencoder (VAE), and the text encoders. Evaluation combines (i) statistical distances to real SAR amplitude distributions, (ii) textural similarity via Gray-Level Co-occurrence Matrix (GLCM) descriptors, and (iii) semantic alignment using a SAR-specialized CLIP model. Our results show that a hybrid strategy-full UNet tuning with LoRA on the text encoders and a learned token embedding-best preserves SAR geometry and texture while maintaining prompt fidelity. The framework supports text-based control and multimodal conditioning (e.g., segmentation maps, TerraSAR-X, or optical guidance), opening new paths for large-scale SAR scene data augmentation and unseen scenario simulation in Earth observation.