CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present CatalogStitch, a set of techniques that help put product images into backgrounds automatically without needing users to fix masks or hidden parts manually. Their method adjusts the area where the product is placed to match different product sizes and perfectly preserves any objects that cover parts of the scene. They also created CatalogStitch-Eval, a test set to measure how well these methods work in tricky situations. Testing with three existing compositing models, they showed that their techniques consistently make the process easier and more accurate for making product catalogs.
generative object compositingmask computationocclusion restorationaspect-ratio mismatchcatalog image generationmodel-agnostic techniquesbenchmark evaluationcontent creation automation
Authors
Sanyam Jain, Pragya Kandari, Manit Singhal, He Zhang, Soo Ye Kim
Abstract
Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world catalog image generation, these methods require tedious manual intervention: users must carefully adjust masks when product dimensions differ, and painstakingly restore occluded elements post-generation. We present CatalogStitch, a set of model-agnostic techniques that automate these corrections, enabling user-friendly content creation. Our dimension-aware mask computation algorithm automatically adapts the target region to accommodate products with different dimensions; users simply provide a product image and background, without manual mask adjustments. Our occlusion-aware hybrid restoration method guarantees pixel-perfect preservation of occluding elements, eliminating post-editing workflows. We additionally introduce CatalogStitch-Eval, a 58-example benchmark covering aspect-ratio mismatch and occlusion-heavy catalog scenarios, together with supplementary PDF and HTML viewers. We evaluate our techniques with three state-of-the-art compositing models (ObjectStitch, OmniPaint, and InsertAnything), demonstrating consistent improvements across diverse catalog scenarios. By reducing manual intervention and automating tedious corrections, our approach transforms generative compositing into a practical, human-friendly tool for production catalog workflows.