TL;DR
RefTon is a streamlined virtual try-on framework that uses unpaired visual references to improve garment realism without complex auxiliary inputs or structural guidance.
Contribution
RefTon introduces a simple, efficient person-to-person virtual try-on method leveraging unpaired references, avoiding complex auxiliary components used in prior approaches.
Findings
Achieves competitive or superior performance on public benchmarks.
Maintains a simple and efficient design compared to state-of-the-art methods.
Utilizes a new dataset with unpaired reference images for training.
Abstract
We introduce RefTon, a flux-based person-to-person virtual try-on framework that enhances garment realism through unpaired visual references. Unlike conventional approaches that rely on complex auxiliary inputs such as body parsing and warped mask or require finely designed extract branches to process various input conditions, RefTon streamlines the process by directly generating try-on results from a source image and a target garment, without the need for structural guidance or auxiliary components to handle diverse inputs. Moreover, inspired by human clothing selection behavior, RefTon leverages additional reference images (the target garment worn on different individuals) to provide powerful guidance for refining texture alignment and maintaining the garment details. To enable this capability, we built a dataset containing unpaired reference images for training. Extensive experiments…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
