aiqbench analysis
This research addresses the scarcity of domain-specific data for Hajj crowd analysis by leveraging generative AI models like Qwen Image Edit to create synthetic training images that preserve sacred-site geometry and specific visual conditions. The study demonstrates that incorporating these reference-guided synthetic images into real datasets effectively reduces error metrics across multiple crowd-counting models, offering a practical solution to annotation limitations in niche environments.
CrowdH-Edit: Reference-Guided Instruction-Based Synthetic Hajj Crowd Image Generation for Crowd Counting
arXiv:2610.23945v1 Announce Type: cross Abstract: The scarcity of domain-specific annotated images remains a major limitation for developing computer-vision systems for Hajj crowd analysis. Existing crowd-counting datasets and unconstrained generative models do not capture Hajj-specific visual conditions, including sacred-site geometry, white-clothed pilgrim crowds, and indoor/outdoor illumination variation. This study presents CrowdH-Edit, a reference-guided, instruction-based framework for synthetic Hajj crowd-image generation. Real Hajj images provide structural references, while textual instructions guide changes in crowd conditions and illumination and help preserve the main scene layout. Stable Diffusion 2.1 and Stable Diffusion XL 1.0 with low-rank adaptation were evaluated as comparative baselines. Qwen Image Edit was used without additional training within a ComfyUI workflow and selected for final dataset construction. The workflow produced CrowdH-Edit, a cleaned pool of 6,122 synthetic images, from which 387 images were selected and annotated to construct CrowdH-Edit-Ann-387. Among the evaluated generation pipelines, Qwen Image Edit achieved the highest semantic-alignment score and the lowest distributional and perceptual distances. Downstream evaluation across five crowd-counting models showed that adding the annotated synthetic subset to real training data reduced mean absolute error for three models and root mean squared error for two. These findings indicate that reference-guided synthetic Hajj imagery can support crowd-counting training, although its benefits depend on the model and evaluation metric.
Abstract:The scarcity of domain-specific annotated images remains a major limitation for developing computer-vision systems for Hajj crowd analysis. Existing crowd-counting datasets and unconstrained generative models do not capture Hajj-specific visual conditions, including sacred-site geometry, white-clothed pilgrim crowds, and indoor/outdoor illumination variation. This study presents CrowdH-Edit, a reference-guided, instruction-based framework for synthetic Hajj crowd-image generation. Real Hajj images provide structural references, while textual instructions guide changes in crowd conditions and illumination and help preserve the main scene layout. Stable Diffusion 2.1 and Stable Diffusion XL 1.0 with low-rank adaptation were evaluated as comparative baselines. Qwen Image Edit was used without additional training within a ComfyUI workflow and selected for final dataset construction. The workflow produced CrowdH-Edit, a cleaned pool of 6,122 synthetic images, from which 387 images were selected and annotated to construct CrowdH-Edit-Ann-387. Among the evaluated generation pipelines, Qwen Image Edit achieved the highest semantic-alignment score and the lowest distributional and perceptual distances. Downstream evaluation across five crowd-counting models showed that adding the annotated synthetic subset to real training data reduced mean absolute error for three models and root mean squared error for two. These findings indicate that reference-guided synthetic Hajj imagery can support crowd-counting training, although its benefits depend on the model and evaluation metric.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.23945 [cs.CV]
(or arXiv:2610.23945v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.23945 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 306 words