| --- |
| datasets: |
| - zhuyr/RRW |
| - nateraw/pascal-voc-2012 |
| base_model: |
| - black-forest-labs/FLUX.1-Kontext-dev |
| --- |
| |
| # Model Card for Model ID |
|
|
| GenSIRR (Rectifying Latent Space for Generative Single-Image Reflection Removal, CVPR 2026) is a generative reflection removal model with great in-the-wild generalization ability. |
|
|
| ## Model Details |
|
|
| ### Model Description |
|
|
|
|
| - **Developed by:** X-Team, School of Software, Tianjin University |
| - **Finetuned from model :** FLUX.1-Kontext |
|
|
| ### Model Sources |
|
|
|
|
| - **Repository:** https://github.com/hainuo-wang/XReflection |
| - **Paper:** Rectifying Latent Space for Generative Single-Image Reflection Removal |
| - **Demo:** https://huggingface.co/spaces/lime-j/GenSIRR |
|
|
|
|
