VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 13753-13762
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62172226)
- National Social Science Foundation of China (24ATQ009)
- Jiangsu Provincial Science and Technology Major Project (BG2024042)
This publication has 17 references indexed in Scilit:
- AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models2025
- AnyDoor: Zero-shot Object-level Image Customization2024
- Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model2024
- Diffusion Model Alignment Using Direct Preference Optimization2024
- Adding Conditional Control to Text-to-Image Diffusion Models2023
- Scalable Diffusion Models with Transformers2023
- DiffCloth: Diffusion Based Garment Synthesis and Manipulation via Structural Cross-modal Semantic Alignment2023
- High-Resolution Image Synthesis with Latent Diffusion Models2022
- Dress Code: High-Resolution Multi-Category Virtual Try-On2022
- VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization2021