Create README.md

README.md

@@ -0,0 +1,44 @@
+<h1>ICLR25: Incorporating Visual Correspondence into Diffusion Model for Visual Try-On</h1>
+This is the official repository for the 
+[Paper](*) 
+"Incorporating Visual Correspondence into Diffusion Model for Visual Try-On"
+
+## Overview
+We novelly propose to explicitly capitalize
+on visual correspondence as the prior to tame diffusion process instead of simply
+feeding the whole garment into UNet as the appearance reference.
+## Installation
+Create a conda environment & Install requirments
+```
+conda create -n SPM-Diff python==3.9.0
+conda activate SPM-Diff
+cd SPM-Diff-main 
+pip install -r requirements.txt
+```
+## Semantic Point Matching
+In SPM, a set of semantic points on the garment are first sampled and matched to the
+corresponding points on the target person via local flow warping. Then, these 2D cues are augmented
+into 3D-aware cues with depth/normal map, which act as semantic point matching to supervise
+diffusion model.
+
+You can directly download the [Semantic Point Feature](*) or follow the instructions in [preprocessing.md](*) to extract the Semantic Point Feature yourself.
+
+## Dataset
+You can download the VITON-HD dataset from [here](https://github.com/xiezhy6/GP-VTON) <br>
+For inference, the following dataset structure is required: <br>
+```
+test
+|-- image
+|-- masked_vton_img 
+|-- warp-cloth
+|-- cloth
+|-- cloth_mask
+|-- point
+```
+## Inference
+Please download the pre-trained model from [Google Link](*)
+```
+sh inference.sh
+```
+## Acknowledgement
+Thanks the contribution of [LaDI-VTON](https://github.com/miccunifi/ladi-vton) and [GP-VTON](https://github.com/xiezhy6/GP-VTON).