Research

Paper

AI LLM March 10, 2026

BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off

Authors

Shuang Liu, Ao Yu, Linkang Cheng, Xiwen Huang, Li Zhao, Junhui Liu, Zhiting Lin, Yu Liu

Abstract

Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF as direct image translation driven by local masks or text-only prompts, overlooking the gap between on-body appearances and flat layouts. This gap frequently leads to inconsistent completion in unobserved regions and unstable garment structure. We propose BridgeDiff, a diffusion-based framework that explicitly bridges human-centric observations and flat-garment synthesis through two complementary components. First, the Garment Condition Bridge Module (GCBM) builds a garment-cue representation that captures global appearance and semantic identity, enabling robust inference of continuous details under partial visibility. Second, the Flat Structure Constraint Module (FSCM) injects explicit flat-garment structural priors via Flat-Constraint Attention (FC-Attention) at selected denoising stages, improving structural stability beyond text-only conditioning. Extensive experiments on standard VTOFF benchmarks show that BridgeDiff achieves state-of-the-art performance, producing higher-quality flat-garment reconstructions while preserving fine-grained appearance and structural integrity.

Metadata

arXiv ID: 2603.09236
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09236v1</id>\n    <title>BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off</title>\n    <updated>2026-03-10T06:12:32Z</updated>\n    <link href='https://arxiv.org/abs/2603.09236v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09236v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF as direct image translation driven by local masks or text-only prompts, overlooking the gap between on-body appearances and flat layouts. This gap frequently leads to inconsistent completion in unobserved regions and unstable garment structure. We propose BridgeDiff, a diffusion-based framework that explicitly bridges human-centric observations and flat-garment synthesis through two complementary components. First, the Garment Condition Bridge Module (GCBM) builds a garment-cue representation that captures global appearance and semantic identity, enabling robust inference of continuous details under partial visibility. Second, the Flat Structure Constraint Module (FSCM) injects explicit flat-garment structural priors via Flat-Constraint Attention (FC-Attention) at selected denoising stages, improving structural stability beyond text-only conditioning. Extensive experiments on standard VTOFF benchmarks show that BridgeDiff achieves state-of-the-art performance, producing higher-quality flat-garment reconstructions while preserving fine-grained appearance and structural integrity.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-10T06:12:32Z</published>\n    <arxiv:comment>33 pages, 16 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Shuang Liu</name>\n    </author>\n    <author>\n      <name>Ao Yu</name>\n    </author>\n    <author>\n      <name>Linkang Cheng</name>\n    </author>\n    <author>\n      <name>Xiwen Huang</name>\n    </author>\n    <author>\n      <name>Li Zhao</name>\n    </author>\n    <author>\n      <name>Junhui Liu</name>\n    </author>\n    <author>\n      <name>Zhiting Lin</name>\n    </author>\n    <author>\n      <name>Yu Liu</name>\n    </author>\n  </entry>"
}