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

TL;DR

BridgeDiff is a diffusion-based framework that improves virtual try-off by explicitly connecting human observations with flat-garment synthesis, resulting in more accurate and stable garment reconstructions.

Contribution

It introduces a novel approach with two modules that bridge human-centric data and flat-garment synthesis, enhancing structural stability and detail inference.

Findings

Achieves state-of-the-art results on standard benchmarks.

Produces higher-quality, structurally stable flat-garment reconstructions.

Effectively preserves fine-grained appearance details.

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.