# RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on

arXiv: https://arxiv.org/abs/2204.11258 · HTML: https://mlsanity.com/paper/2204.11258/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 24 Apr 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization](https://mlsanity.com/paper/2103.16874/) (2021)
- [VITON: An Image-based Virtual Try-on Network](https://mlsanity.com/paper/1711.08447/) (2017)
- [SEAN: Image Synthesis with Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/1911.12861/) (2019)
- [FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping](https://mlsanity.com/paper/1912.13457/) (2019)
- [Toward Characteristic-Preserving Image-based Virtual Try-On Network](https://mlsanity.com/paper/1807.07688/) (2018)
- [Towards Photo-Realistic Virtual Try-On by Adaptively GeneratingleftrightarrowPreserving Image Content](https://mlsanity.com/paper/2003.05863/) (2020)
- [Parser-Free Virtual Try-on via Distilling Appearance Flows](https://mlsanity.com/paper/2103.04559/) (2021)
- [Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsing](https://mlsanity.com/paper/1703.05446/) (2017)
- [Towards Multi-pose Guided Virtual Try-on Network](https://mlsanity.com/paper/1902.11026/) (2019)
- [Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On](https://mlsanity.com/paper/2007.02721/) (2020)
- [Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generation](https://mlsanity.com/paper/1912.12215/) (2019)
- [Mask-Guided Portrait Editing with Conditional GANs](https://mlsanity.com/paper/1905.10346/) (2019)

## Built on by (most cited first, 6 of 6)

- [Image-Based Virtual Try-On: A Survey](https://mlsanity.com/paper/2311.04811/) (2023)
- [Deep Learning Technique for Human Parsing: A Survey and Outlook](https://mlsanity.com/paper/2301.00394/) (2023)
- [PASTA-GAN++: A Versatile Framework for High-Resolution Unpaired Virtual Try-on](https://mlsanity.com/paper/2207.13475/) (2022)
- [DM-VTON: Distilled Mobile Real-time Virtual Try-On](https://mlsanity.com/paper/2308.13798/) (2023)
- [PFDM: Parser-Free Virtual Try-on via Diffusion Model](https://mlsanity.com/paper/2402.03047/) (2024)
- [Shape-Guided Clothing Warping for Virtual Try-On](https://mlsanity.com/paper/2504.15232/) (2025)

## Abstract (arXiv)

Virtual try-on(VTON) aims at fitting target clothes to reference person images, which is widely adopted in e-commerce.Existing VTON approaches can be narrowly categorized into Parser-Based(PB) and Parser-Free(PF) by whether relying on the parser information to mask the persons' clothes and synthesize try-on images. Although abandoning parser information has improved the applicability of PF methods, the ability of detail synthesizing has also been sacrificed. As a result, the distraction from original cloth may persistin synthesized images, especially in complicated postures and high resolution applications. To address the aforementioned issue, we propose a novel PF method named Regional Mask Guided Network(RMGN). More specifically, a regional mask is proposed to explicitly fuse the features of target clothes and reference persons so that the persisted distraction can be eliminated. A posture awareness loss and a multi-level feature extractor are further proposed to handle the complicated postures and synthesize high resolution images. Extensive experiments demonstrate that our proposed RMGN outperforms both state-of-the-art PB and PF methods.Ablation studies further verify the effectiveness ofmodules in RMGN.