What question did this study set out to answer?

The aim is to enhance rooftop segmentation accuracy from aerial images using parameter-efficient adaptations of generative models.

April 1, 2026Buildings0 citationsOpen Access

View Full Paper

Parameter-Efficient Adaptation of Generative-Foundation (Flux, Qwen) vs. Zero-Shot (Gemini, SAM3) Models for Aerial Image Segmentation

DSDina ShataQueensland University of Technology SDSimon DenmanQueensland University of Technology SOSara OmraniQueensland University of Technology

Key Points

The aim is to enhance rooftop segmentation accuracy from aerial images using parameter-efficient adaptations of generative models.
Evaluated three model paradigms: zero-shot models, segmentation-first baseline, and LoRA-adapted models.
Used aerial imagery from Brisbane, split 80/20 into training and testing datasets.
Fine-tuned models for 250 to 5000 steps depending on the paradigm.
Gemini model achieved a strong zero-shot baseline with IoU of 85% and Dice of 91%.
SAM3 also performed well with IoU of 84% and Dice of 91%, but had increased false negatives in complex scenes.
LoRA adaptation led to improved scores: FLUX models reached IoU of 89% and Dice of 94% at their best, outperforming others.

Abstract

Accurate rooftop segmentation from aerial imagery is essential for large-scale urban analysis, including applications such as solar potential assessment and urban monitoring. However, it remains constrained by the high cost of dense annotation and the limited generalisation of supervised models across heterogeneous urban morphologies. This study investigates binary rooftop segmentation for fine-tuning large image-editing foundation models using parameter-efficient Low-Rank Adaptation (LoRA). Using parts of Brisbane metropolitan dataset (split 80/20 into 97 training and 24 testing tiles), three paradigms were evaluated under a unified protocol: zero-shot image-editing models (including Gemini 3 Pro), a segmentation-first baseline (Segment Anything Model 3, SAM3), and LoRA-adapted diffusion models (FLUX.1 Kontext, FLUX.2, and Qwen Image Edit 2509) fine-tuned each 250 steps up to 5000 steps. Evaluated under zero-shot conditions, the generative models demonstrated varying levels of boundary fidelity. The Gemini model achieved a strong zero-shot baseline with IoU, Dice scores of 85%, 91%, followed by the SAM3 baseline, which also achieved a stable 84%, 91% but exhibited increased false negatives in visually complex scenes. The tested diffusion models (FLUX.1 Kontext, FLUX.2, and Qwen) showed more limited initial spatial overlap, scoring 45%, 55%, 67%, 78%, and 33%, 46%, respectively. Following LoRA adaptation, the FLUX and Qwen models showed substantial improvements, with their respective IoU, Dice metrics increasing to 89%, 94%, 82%, 90%, and 87%, 93%. FLUX.1 Kontext achieved the strongest overall performance at step 4250, yielding a mean IoU of 89% (SD = 3.16%) and a pixel accuracy exceeding 96%. These results demonstrate that parameter-efficient fine-tuning, combined with rigorous evaluation under class-imbalanced conditions, can transform general-purpose generative models into competitive, scalable spatial analysis tools that match or exceed both dedicated segmentation baselines and strong zero-shot multimodal models.

Ask AI

Helpful

Bookmark

View Full Paper

Ask AI

Helpful

Bookmark

View Full Paper

Parameter-Efficient Adaptation of Generative-Foundation (Flux, Qwen) vs. Zero-Shot (Gemini, SAM3) Models for Aerial Image Segmentation

Key Points

Abstract

Cite This Study