MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance Forecasting
Official implementation of the paper MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance Forecasting accepted at the FashionAI workshop, organized in conjunction with the European Conference on Computer Vision (ECCV 2024).
The code will be available soon.
Andrea Avogaro1, Luigi Capogrosso1, Franco Fummi1, Marco Cristani1
1 Department of Engineering for Innovation Medicine, University of Verona, Italy
If you use MDiFF, please, cite the following paper:
TBA.