Update model card with paper links and improved metadata

README.md

@@ -1,7 +1,12 @@
 ---
-license:  cc-by-nc-4.0
-pipeline_tag: video-to-video
 library_name: diffusers
+license: cc-by-nc-4.0
+pipeline_tag: image-to-image
+tags:
+- video-to-video
+- video-object-removal
+- video-inpainting
+- cvpr
 ---
 
 <div align="center">
@@ -23,27 +28,27 @@ library_name: diffusers
   </p>
   <p>
     <a href="https://henghuiding.com/EffectErase/" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/🐳-Project%20Page-blue" alt="Project Page" /></a>
-    <a href="https://cvpr.thecvf.com/virtual/2026/papers.html" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/Paper-CVPR%202026-green" alt="Paper" /></a>
+    <a href="https://huggingface.co/papers/2603.19224" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/Paper-CVPR%202026-green" alt="Paper" /></a>
     <a href="https://github.com/FudanCVL/EffectErase" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/GitHub-FudanCVL%2FEffectErase-181717?logo=github" alt="GitHub" /></a>
-    <a href="http://arxiv.org/" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/arXiv-EffectErase-red" alt="arXiv" /></a>
+    <a href="https://huggingface.co/papers/2603.19224" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/arXiv-2603.19224-red" alt="arXiv" /></a>
     <a href="https://huggingface.co/datasets/FudanCVL/EffectErase" target="_blank" rel="noreferrer"><img src="https://img.shields.io/badge/%F0%9F%A4%97%20Dataset-Hugging%20Face-yellow" alt="Dataset" /></a>
   </p>
 </div>
 
-This repository provides the checkpoint `EffectErase.ckpt` for **EffectErase**.
+This repository provides the checkpoint `EffectErase.ckpt` for **EffectErase**, as presented in the paper [EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing](https://huggingface.co/papers/2603.19224).
 
 <img src="assets/teaser.gif" alt="teaser" />
 
 ## Abstract
 
-Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds. Recent diffusion-based video inpainting and object removal methods can remove the objects but often struggle to erase these effects and to synthesize coherent backgrounds. Beyond method limitations, progress is further hampered by the lack of a comprehensive dataset that systematically captures common object effects across varied environments for training and evaluation. To address this, we introduce **VOR** (**V**ideo **O**bject **R**emoval), a large-scale dataset that provides diverse paired videos, each consisting of one video where the target object is present with its effects and a counterpart where the object and effects are absent, with corresponding object masks. VOR contains 60k high-quality video pairs from captured and synthetic sources, covers five effects types, and spans a wide range of object categories as well as complex, dynamic multi-object scenes. Building on VOR, we propose ***EffectErase***, an effect-aware video object removal method that treats video object insertion as the inverse auxiliary task within a reciprocal learning scheme. The model includes task-aware region guidance that focuses learning on affected areas and enables flexible task switching. Then, an insertion–removal consistency objective that encourages complementary behaviors and shared localization of effect regions and structural cues. Trained on VOR, EffectErase achieves superior performance in extensive experiments, delivering high-quality video object effect erasing across diverse scenarios.
+Video object removal aims to eliminate dynamic target objects and their visual effects, such as deformation, shadows, and reflections, while restoring seamless backgrounds. Current methods often struggle to erase these effects and synthesize coherent backgrounds. To address this, we introduce **VOR** (**V**ideo **O**bject **R**emoval), a large-scale dataset of 60K high-quality video pairs covering various object effects. Building on VOR, we propose ***EffectErase***, an effect-aware video object removal method that treats video object insertion as a reciprocal learning task. The model includes task-aware region guidance and an insertion-removal consistency objective to ensure high-quality video object effect erasing across diverse scenarios.
 
 ## Quick Start
 
 1. Setup repository and environment
 
    ```bash
-   git clone git@github.com:FudanCVL/EffectErase.git
+   git clone https://github.com/FudanCVL/EffectErase.git
    cd EffectErase
    pip install -e .
    ```
@@ -61,18 +66,13 @@ Video object removal aims to eliminate dynamic target objects and their visual e
    bash script/test_remove.sh
    ```
 
-   You can edit `script/test_remove.sh` and change these three paths to use your own data:
-
-   - `--fg_bg_path`
-   - `--mask_path`
-   - `--output_path`
-
-   `--mask_path` is a mask video generated by SAM2.1 (`sam2.1_hiera_b+`), aligned with `--fg_bg_path`.
+   You can edit `script/test_remove.sh` and change these paths to use your own data:
+   - `--fg_bg_path`: Path to the input video.
+   - `--mask_path`: Path to the mask video (e.g., generated by SAM2.1).
+   - `--output_path`: Path for the saved results.
 
 ## BibTeX
 
-Please consider to cite:
-
 ```bibtex
 @inproceedings{fu2026effecterase,
   title={EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing},
@@ -84,5 +84,4 @@ Please consider to cite:
 
 ## Contact
 
-If you have any questions, please feel free to reach me out at aleeyanger@gmail.com.
-
+If you have any questions, please feel free to reach out at aleeyanger@gmail.com.