Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Yihan, Ge, Mengying
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.02038
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917184562790400
author Zhu, Yihan
Ge, Mengying
author_facet Zhu, Yihan
Ge, Mengying
contents Virtual Try-Off (VTOFF) is a challenging multimodal image generation task that aims to synthesize high-fidelity flat-lay garments under complex geometric deformation and rich high-frequency textures. Existing methods often rely on lightweight modules for fast feature extraction, which struggles to preserve structured patterns and fine-grained details, leading to texture attenuation during generation.To address these issues, we propose AlignVTOFF, a novel parallel U-Net framework built upon a Reference U-Net and Texture-Spatial Feature Alignment (TSFA). The Reference U-Net performs multi-scale feature extraction and enhances geometric fidelity, enabling robust modeling of deformation while retaining complex structured patterns. TSFA then injects the reference garment features into a frozen denoising U-Net via a hybrid attention design, consisting of a trainable cross-attention module and a frozen self-attention module. This design explicitly aligns texture and spatial cues and alleviates the loss of high-frequency information during the denoising process.Extensive experiments across multiple settings demonstrate that AlignVTOFF consistently outperforms state-of-the-art methods, producing flat-lay garment results with improved structural realism and high-frequency detail fidelity.
format Preprint
id arxiv_https___arxiv_org_abs_2601_02038
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AlignVTOFF: Texture-Spatial Feature Alignment for High-Fidelity Virtual Try-Off
Zhu, Yihan
Ge, Mengying
Computer Vision and Pattern Recognition
Virtual Try-Off (VTOFF) is a challenging multimodal image generation task that aims to synthesize high-fidelity flat-lay garments under complex geometric deformation and rich high-frequency textures. Existing methods often rely on lightweight modules for fast feature extraction, which struggles to preserve structured patterns and fine-grained details, leading to texture attenuation during generation.To address these issues, we propose AlignVTOFF, a novel parallel U-Net framework built upon a Reference U-Net and Texture-Spatial Feature Alignment (TSFA). The Reference U-Net performs multi-scale feature extraction and enhances geometric fidelity, enabling robust modeling of deformation while retaining complex structured patterns. TSFA then injects the reference garment features into a frozen denoising U-Net via a hybrid attention design, consisting of a trainable cross-attention module and a frozen self-attention module. This design explicitly aligns texture and spatial cues and alleviates the loss of high-frequency information during the denoising process.Extensive experiments across multiple settings demonstrate that AlignVTOFF consistently outperforms state-of-the-art methods, producing flat-lay garment results with improved structural realism and high-frequency detail fidelity.
title AlignVTOFF: Texture-Spatial Feature Alignment for High-Fidelity Virtual Try-Off
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.02038