Cascaded Diffusion Models for Try-On

Written by backpropagation | Published 2024/10/06
Tech Story Tags: ai-in-fashion | deep-learning | tryondiffusion | parallel-unet | photorealistic-fashion | fashion-technology | body-pose-adaptation | image-based-virtual-try-on

TLDR

The virtual try-on system uses a three-stage diffusion model with Parallel-UNet at its core. The base model generates a 128x128 try-on result, augmented with noise conditioning. This result is upscaled to 256x256 and finally to 1024x1024 using an Efficient-UNet for super-resolution. Noise conditioning is applied at each stage to handle inaccuracies in human parsing and pose estimation, ensuring high-quality outputs.via the TL;DR App

Authors:

(1) Luyang Zhu, University of Washington and Google Research, and work done while the author was an intern at Google;

(2) Dawei Yang, Google Research;

(3) Tyler Zhu, Google Research;

(4) Fitsum Reda, Google Research;

(5) William Chan, Google Research;

(6) Chitwan Saharia, Google Research;

(7) Mohammad Norouzi, Google Research;

(8) Ira Kemelmacher-Shlizerman, University of Washington and Google Research.

Table of Links

Abstract and 1. Introduction

2. Related Work

3.1. Cascaded Diffusion Models for Try-On

3.2. Parallel-UNet

5. Summary and Future Work and References

Appendix

A. Implementation Details

B. Additional Results

3.1. Cascaded Diffusion Models for Try-On

Our cascaded diffusion models consist of one base diffusion model and two super-resolution (SR) diffusion models.

This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license.

Written by backpropagation | Uncovering hidden patterns with backpropagation, a powerful but often misunderstood algorithm shaping AI insights.

Published by HackerNoon on 2024/10/06