1-2-1: Renaissance of Single-Network Paradigm for Virtual Try-On

TL;DR

This paper introduces MNVTON, a novel single-network virtual try-on method that uses modality-specific normalization to achieve high-quality, detailed results, rivaling dual-network approaches with improved efficiency.

Contribution

Proposes a single-network VTON framework with modality-specific normalization, eliminating the need for dual networks and reducing computational overhead.

Findings

Achieves higher-quality, detailed VTON results for images and videos.

Matches or surpasses dual-network methods in performance.

Offers a more scalable and efficient VTON solution.

Abstract

Virtual Try-On (VTON) has become a crucial tool in ecommerce, enabling the realistic simulation of garments on individuals while preserving their original appearance and pose. Early VTON methods relied on single generative networks, but challenges remain in preserving fine-grained garment details due to limitations in feature extraction and fusion. To address these issues, recent approaches have adopted a dual-network paradigm, incorporating a complementary "ReferenceNet" to enhance garment feature extraction and fusion. While effective, this dual-network approach introduces significant computational overhead, limiting its scalability for high-resolution and long-duration image/video VTON applications. In this paper, we challenge the dual-network paradigm by proposing a novel single-network VTON method that overcomes the limitations of existing techniques. Our method, namely MNVTON, introduces a Modality-specific Normalization strategy that separately processes text, image and video inputs, enabling them to share the same attention layers in a VTON network. Extensive experimental results demonstrate the effectiveness of our approach, showing that it consistently achieves higher-quality, more detailed results for both image and video VTON tasks. Our results suggest that the single-network paradigm can rival the performance of dualnetwork approaches, offering a more efficient alternative for high-quality, scalable VTON applications.