Update README.md

README.md

@@ -1,5 +1,4 @@
 ---
-license: mit
 tags:
 - image-to-image
 - reflection-removal
@@ -7,8 +6,6 @@ tags:
 - computer-vision
 - dinov3
 - surgical-imaging
-language:
-- en
 base_model:
 - facebook/dinov3-vitl16-pretrain-lvd1689m
 - Ruicheng/moge-2-vitl-normal
@@ -24,35 +21,26 @@ base_model:
 [![Licence](https://img.shields.io/badge/MIT-License-1E811F)](https://mit-license.org/)
 
 UnReflectAnything inputs any RGB image and removes specular highlights, returning a clean diffuse-only outputs. We trained UnReflectAnything by synthetizing specularities and supervising in DINOv3 feature space.
-
 UnReflectAnything works on both natural indoor and surgical/endoscopic domain data. 
 
----
-
 ## Architecture
 ![Architecture](https://raw.githubusercontent.com/alberto-rota/UnReflectAnything/refs/heads/main/assets/architecture.png)
 
-* **<font color="#a001e0">Encoder E <font>**: Processes the input image $\mathbf{I}$ to extract a rich latent representation, $\mathbf{F}_\ell$. This is the off-the-shelf pretrained [DINOv3-large](https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m) 
-* **<font color="#0167ff">Reflection Predictor H</font> **: Predicts a soft highlight mask (**H**), identifying areas of specular highlights.
-
-* **Masking Operation</font>**: A binary mask **P** is derived from the prediction and applied to the feature map: This removes features contaminated by reflections, leaving "holes" in the data.
-
+* **<font color="#a001e0">Encoder E </font>**: Processes the input image to extract a rich latent representation. This is the off-the-shelf pretrained [DINOv3-large](https://huggingface.co/facebook/dinov3-vitl16-pretrain-lvd1689m) 
+* **<font color="#0167ff">Reflection Predictor H</font>**: Predicts a soft highlight mask (**H**), identifying areas of specular highlights.
+* **Masking Operation**: A binary mask **P** is derived from the prediction and applied to the feature map: This removes features contaminated by reflections, leaving "holes" in the data.
 * **<font color="#23ac2c">Token Inpainter T</font>**: Acts as a neural in-painter. It processes the masked features and uses the surrounding clean context prior and a learned mask token to synthesize the missing information in embedding space, producing the completed feature map $\mathbf{F}_{\text{comp}}$.
-
-* **<font color="#ff7700">Decoder D </font> **: Project the completed features back into the pixel space to generate the final, reflection-free image $\mathbf{I}_{\text{diff}}$.
+* **<font color="#ff7700">Decoder D </font>**: Project the completed features back into the pixel space to generate the final, reflection-free image
 
 ---
-
 ## Training Strategy
 We train UnReflectAnything with **Synthetic Specular Supervision** by inferring 3D geometry from [MoGe-2](https://wangrc.site/MoGe2Page/) and rendering highlights with a Blinn-Phong reflection model. We randomly sample the light source position in 3D space at every training iteration enhance etherogeneity.
 
 ![SupervisionExamples](https://raw.githubusercontent.com/alberto-rota/UnReflectAnything/refs/heads/main/assets/highlights.png)
 
 We train the model in two stages
-1.  **DPT Decoder Pre-Training**: The **<font color="#ff7700">Decoder</font>** is first pre-trained in an autoencoder configuration ($\min_{\theta} \mathcal{L}(M_{\theta}(\mathbf{I}), \mathbf{I})$) to ensure it can reconstruct realistic RGB textures from the DINOV3 latent space.
-2.  **End-to-End Refinement**: The full pipeline is then trained to predict reflection masks from $\mathit{\textcolor{0167ff}{H}}$, and fill them using the **<font color="#38761D">Token Inpainter</font>**, ensuring the final output is both visually consistent and physically accurate. The decoder is also fine-tuned at this stage
-
-
+1.  **DPT Decoder Pre-Training**: The **<font color="#ff7700">Decoder</font>** is first pre-trained in an autoencoder configuration to ensure it can reconstruct realistic RGB textures from the DINOV3 latent space.
+2.  **End-to-End Refinement**: The full pipeline is then trained to predict reflection masks and fill them using the **<font color="#38761D">Token Inpainter</font>**, ensuring the final output is both visually consistent and physically accurate. We utilize the Synthetic Specular Supervision to generate ground-truth signals in feature space. The decoder is also fine-tuned at this stage
 
 ## Weights
 Install the API and CLI on a **Python>=3.11** environment with 
@@ -66,7 +54,6 @@ unreflectanything download --weights
 to download the `.pth` weights in the package cache dir. The cache dir is usually at `.cache/unreflectanything`
 
 ---
-
 ### Basic Python Usage
 
 ```python
@@ -86,7 +73,6 @@ unreflectanything.inference("input_with_highlights.png", output="diffuse_result.
 Refer to the [Wiki](https://github.com/alberto-rota/UnReflectAnything/wiki) for all details on the API endpoints
 
 ---
-
 ### CLI Overview
 
 The package provides a comprehensive command-line interface via `ura`, `unreflect`, or `unreflectanything`.
@@ -98,7 +84,6 @@ The package provides a comprehensive command-line interface via `ura`, `unreflec
 Refer to the [Wiki](https://github.com/alberto-rota/UnReflectAnything/wiki) for all details on the CLI endpoints
 
 ---
-
 ## Citation
 
 If you use UnReflectAnything in your research or pipeline, please cite our paper: