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

2026-03-10

AI Summary

This work addresses the challenges of inconsistent details and structural instability in recovering standardized flat-layout garments from dressed human images in virtual try-on, which arise from neglecting the discrepancy between on-body appearance and flat garment geometry. To tackle this, we propose a novel diffusion-based framework that incorporates a Garment Condition Bridging Module (GCBM) to model global appearance semantics and a Flat-layout Structural Constraint Module (FSCM) equipped with a planar-constrained attention mechanism to inject explicit geometric priors during the diffusion denoising process. Experimental results on the VTOFF benchmark demonstrate that our method significantly outperforms existing approaches, achieving state-of-the-art performance in both structural integrity and detail consistency of reconstructed flat garments.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Virtual try-off
• Flat-garment synthesis
• Garment structure
• Image-to-garment translation
• Appearance-structure gap

Innovation

• BridgeDiff
• Garment Condition Bridge Module
• Flat Structure Constraint Module
• diffusion model
• virtual try-off