Official Gradio demo for ObjectClear: Complete Object Removal via Object-Effect Attention.
🔥 ObjectClear is an object removal model that can jointly eliminate the target object and its associated effects leveraging Object-Effect Attention, while preserving background consistency.
🖼️ Try to drop your image, assign the target masks with a few clicks, and get the object removal results!

Note: All input images are temporarily resized (shorter side = 512 pixels) during inference to match the training resolution. Final outputs are restored to the original resolution.
Point Prompt

Click to add positive or negative point for target mask
Strength

0.99 better preserves the background and color; use 1.0 if object/shadow is not fully removed (default: 0.99)
1 10
0 1000000
1 40
0:00 / 0:00

Examples
Click below to load example images

If ObjectClear is helpful, please help to star the Github Repo. Thanks!

📑 Citation
If our work is useful for your research, please consider citing:

@InProceedings{zhao2025ObjectClear,
    title     = {{ObjectClear}: Complete Object Removal via Object-Effect Attention},
    author    = {Zhao, Jixin and Zhou, Shangchen and Wang, Zhouxia and Yang, Peiqing and Loy, Chen Change},
    booktitle = {arXiv preprint arXiv:2505.22636},
    year      = {2025}
    }

📧 Contact
If you have any questions, please feel free to reach me out at jixinzhao0101@gmail.com.
👏 Acknowledgement
This demo is adapted from MatAnyone, and leveraging segmentation capabilities from Segment Anything. Thanks for their awesome works!