GarmentZoom: Generating Zoomable Images from Garment Listings

2026-06-28

AI Summary

This work addresses the disjointed representation of full-view and detail images in online fashion product displays, which necessitates frequent view switching. To overcome this limitation, the authors propose a continuous zoom-in detail enhancement method that operates without requiring spatial alignment. By integrating reference-based super-resolution with a scale-adaptive detail synthesis mechanism, a single model generates high-fidelity textures across a continuous zoom range from 3× to 20×, generalizing effectively across diverse garment categories. This approach achieves, for the first time, category- and scale-agnostic detail transfer without per-instance fine-tuning, delivering image quality comparable to instance-level optimization methods while substantially reducing training costs and enabling smooth interactive zooming experiences.

Abstract

Online product listings for garments often include an overview photo and a close-up to show garment details. However, each photo focuses on either field of view or garment detail, forcing users to alternate between views and breaking browsing continuity. We present GarmentZoom, a system that enhances the full-view photo to match the fidelity of its accompanying close-up, enabling seamless zoom-and-pan exploration. Unlike standard reference-based super-resolution, our setting involves close-up references that are spatially unaligned with the full view, and scale factors that vary substantially across garments 3-20$\times$. Prior work typically relies on alignment to transfer details or requires per-instance fine-tuning to memorize them. Instead, we train a single model that supports a continuous range of scales across diverse garments. Our approach synthesizes details without requiring spatial alignment and matches the quality of per-instance methods with a fraction of the training cost.

Problem

• garment imaging
• zoomable images
• super-resolution
• spatial misalignment
• scale variation

Innovation

• GarmentZoom
• reference-based super-resolution
• spatially unaligned
• continuous scale synthesis
• detail enhancement