GarmentZoom: Generating Zoomable Images from Garment Listings
For e-commerce platforms, this improves user browsing experience by eliminating the need to alternate between overview and close-up photos.
GarmentZoom enhances full-view garment photos to match the fidelity of close-up references, enabling seamless zoom-and-pan exploration. The method supports continuous scale factors (3-20x) without spatial alignment, matching per-instance quality at a fraction of training cost.
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.