Update README.md

README.md

@@ -10,12 +10,12 @@
 
 [HKUST](https://hkust.edu.hk/)<sup>1</sup>, [Horizon Robotics](https://en.horizon.auto/)<sup>2</sup>, [CUHK](https://cuhk.edu.hk/)<sup>3</sup>, [NJU](https://www.nju.edu.cn/)<sup>4</sup><br>
 <sup>*</sup> Corresponding Author, <sup>§</sup> Project Leader
-<br><br><image src='assets/teaser.png'/>
+<br><br><image src='https://huggingface.co/mkjia/MGVQ/resolve/main/assets/teaser.png'/>
 </div>
 
 
 ## 🚀News
-- ```[August 2025]``` Achieve SOTA at paperwithcode leaderboards: Image Reconstruction on ImageNet and UHDBench. <image src='assets/SOTA_recon_fid_imagenet_badge.jpg'/> <image src='assets/SOTA_recon_PSNR_UHD_badge.jpg'/>
+- ```[August 2025]``` Achieve SOTA at paperwithcode leaderboards: Image Reconstruction on ImageNet and UHDBench. <image src='https://huggingface.co/mkjia/MGVQ/raw/main/assets/SOTA_recon_fid_imagenet_badge.jpg'/> <image src='https://huggingface.co/mkjia/MGVQ/raw/main/assets/SOTA_recon_PSNR_UHD_badge.jpg'/>
 - ```[August 2025]``` Released Inference Code
 - ```[August 2025]``` Released [model zoo](https://huggingface.co/mkjia/MGVQ/tree/main).
 - ```[August 2025]``` Released dataset for ultra-high-definition image reconstruction evaluation. Our proposed super-resolution image reconstruction [UHDBench dataset](https://huggingface.co/datasets/mkjia/UHDBench/tree/main) is released.
@@ -78,23 +78,23 @@ python3 evaluator.py /path/to/your/VIRTUAL_imagenet256_labeled.npz /path/to/your
 ## 🗄️Demos
 - 🔥 Qualitative reconstruction images with $16$ x downsampling on $2560$ x $1440$ UHDBench dataset. 
 
-<image src='assets/qual_recon.png'/>
+<image src='https://huggingface.co/mkjia/MGVQ/resolve/main/assets/qual_recon.png'/>
 
 - 🔥 Qualitative class-to-image generation of Imagenet. The classes are dog(Golden Retriever and Husky), cliff, and bald eagle.
 
-<image src='assets/qual_gen.png'/>
+<image src='https://huggingface.co/mkjia/MGVQ/resolve/main/assets/qual_gen.png'/>
 
 - 🔥 Reconstruction evaluation on 256×256 ImageNet benchmark. 
 
-<image src='assets/recon_tab_1.jpg'/>
+<image src='https://huggingface.co/mkjia/MGVQ/resolve/main/assets/recon_tab_1.jpg'/>
 
 - 🔥 Zero-shot reconstruction evaluation with a downsample ratio of 16 on 512×512 datasets.
 
-<image src='assets/recon_tab_2.jpg'/>
+<image src='https://huggingface.co/mkjia/MGVQ/resolve/main/assets/recon_tab_2.jpg'/>
 
 - 🔥 Zero-shot reconstruction evaluation with a downsample ratio of 16 on 2560×1440 datasets.
 
-<div align="center"><image src='assets/recon_tab_3.jpg'/></image></div>
+<div align="center"><image src='https://huggingface.co/mkjia/MGVQ/resolve/main/assets/recon_tab_3.jpg'/></image></div>
   
 ## 🗄️Demos