Upload weights, notebooks, sample images

README.md

@@ -1,13 +1,12 @@
 ---
-tags:
-- image-to-image
-- reflection-removal
-- highlight-removal
-- computer-vision
-- dinov3
-- surgical-imaging
 license: mit
-pipeline_tag: image-to-image
+tags:
+  - image-to-image
+  - reflection-removal
+  - highlight-removal
+  - computer-vision
+  - dinov3
+  - surgical-imaging
 ---
 
 # UnReflectAnything
@@ -16,30 +15,43 @@ pipeline_tag: image-to-image
 [![PyPI](https://img.shields.io/pypi/v/unreflectanything?color=76b1f3&label=pip%20install&logo=python&logoColor=76b1f3)](https://pypi.org/project/unreflectanything/)
 [![Paper](https://img.shields.io/badge/Paper-arXiv-B31B1B?logo=arxiv&logoColor=B31B1B)](https://arxiv.org/abs/2512.09583)
 [![Demo](https://img.shields.io/badge/Demo-HF%20-FFD21E?logo=huggingface&logoColor=FFD21E)](https://huggingface.co/spaces/AlbeRota/UnReflectAnything)
+[![Modelcard](https://img.shields.io/badge/Model%20Card-HF%20-FFD21E?logo=huggingface&logoColor=FFD21E)](https://huggingface.co/AlbeRota/UnReflectAnything)
 [![Wiki](https://img.shields.io/badge/API-Wiki-9187FF?logo=wikipedia&logoColor=9187FF)](https://github.com/alberto-rota/UnReflectAnything/wiki)
 [![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 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
+
+
+* **<font color="#a001e0">Encoder</font> ($\mathit{\textcolor{a001e0}{E}}$ )**: 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</font> ($\mathit{\textcolor{0167ff}{H}}$ )**: Predicts a soft highlight mask (**H**), identifying areas of specular highlights.
+
+* **Masking Operation</font> ($\mathit{P}$ )**: A binary mask **P** is derived from the prediction and applied to the feature map: $(1-\mathbf{P}) \odot \mathbf{F}_\ell$. This removes features contaminated by reflections, leaving "holes" in the data.
+
+* **<font color="#23ac2c">Token Inpainter</font> ($\mathit{\textcolor{23ac2c}{T}}$ )**: 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</font> ($\mathit{\textcolor{ff7700}{D}}$ )**: Project the completed features back into the pixel space to generate the final, reflection-free image $\mathbf{I}_{\text{diff}}$.
 
 ---
+
 ## 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 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
+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
+
+
 
 ## Weights
 Install the API and CLI on a **Python>=3.11** environment with 
@@ -53,6 +65,7 @@ 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
@@ -72,6 +85,7 @@ 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`.
@@ -83,6 +97,7 @@ 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:
@@ -100,4 +115,4 @@ If you use UnReflectAnything in your research or pipeline, please cite our paper
 
 ```
 
----
+---