Post
Introducing π¨πWindowSeatπ¨π ββ our new method for removing reflections from photos taken through windows, on planes, in malls, offices, and other glass-filled environments.
Finetuning a foundation diffusion transformer for reflection removal quickly runs up against the limits of what existing datasets and techniques can offer. To fill that gap, we generate physically accurate examples in Blender that simulate realistic glass and reflection effects. This data enables strong performance on both established benchmarks and previously unseen images.
To make this practical, the open-source Apache-2 model builds on Qwen-Image-Edit-2509, a 20B image-editing diffusion transformer that runs on a single GPU and can be fine-tuned in about a day. WindowSeat keeps its use of the underlying DiT cleanly separated from the data and training recipe, allowing future advances in base models to be incorporated with minimal friction.
Try it out with your own photos in this interactive demo:
π€ toshas/windowseat-reflection-removal
Other resources:
π Website: huawei-bayerlab/windowseat-reflection-removal-web
π Paper: Reflection Removal through Efficient Adaptation of Diffusion Transformers (2512.05000)
π€ Model: huawei-bayerlab/windowseat-reflection-removal-v1-0
π Code: https://github.com/huawei-bayerlab/windowseat-reflection-removal
Team: Daniyar Zakarin ( @daniyarzt )*, Thiemo Wandel ( @thiemo-wandel )*, Anton Obukhov ( @toshas ), Dengxin Dai.
*Work done during internships at HUAWEI Bayer Lab
Finetuning a foundation diffusion transformer for reflection removal quickly runs up against the limits of what existing datasets and techniques can offer. To fill that gap, we generate physically accurate examples in Blender that simulate realistic glass and reflection effects. This data enables strong performance on both established benchmarks and previously unseen images.
To make this practical, the open-source Apache-2 model builds on Qwen-Image-Edit-2509, a 20B image-editing diffusion transformer that runs on a single GPU and can be fine-tuned in about a day. WindowSeat keeps its use of the underlying DiT cleanly separated from the data and training recipe, allowing future advances in base models to be incorporated with minimal friction.
Try it out with your own photos in this interactive demo:
π€ toshas/windowseat-reflection-removal
Other resources:
π Website: huawei-bayerlab/windowseat-reflection-removal-web
π Paper: Reflection Removal through Efficient Adaptation of Diffusion Transformers (2512.05000)
π€ Model: huawei-bayerlab/windowseat-reflection-removal-v1-0
π Code: https://github.com/huawei-bayerlab/windowseat-reflection-removal
Team: Daniyar Zakarin ( @daniyarzt )*, Thiemo Wandel ( @thiemo-wandel )*, Anton Obukhov ( @toshas ), Dengxin Dai.
*Work done during internships at HUAWEI Bayer Lab
