IMAGDressing: Interactive Modular Apparel Generation for Virtual Try-On

IMAGDressing is a dataset and framework for interactive modular apparel generation and virtual try-on, released by muzishen for AAAI 2025. It facilitates high-fidelity human image generation with specific controls for garments, poses, and scenes to ensure consistency in virtual dressing applications.

Use Cases

• Training diffusion models for garment-consistent virtual try-on
• Evaluating pose-guided human image synthesis using pose control features
• Developing interactive apparel generation systems with scene-specific backgrounds

Strengths

• AAAI 2025 peer-reviewed research foundation
• Apache-2.0 permissive license
• Supports modular control across three dimensions: garment, pose, and scene

Limitations

• Lack of explicit record count or metadata schema in the primary description
• High computational requirements typical for diffusion model training

Provenance

Source

muzishen, AAAI 2025

Freshness

Last updated September 2025; associated with AAAI 2025 publication.