54 14 35

Anton Obukhov PRO

toshas

AI & ML interests

None yet

Recent Activity

reacted to their post with 😎 about 14 hours ago

Introducing StereoSpace -- our new end-to-end method for turning photos into stereo images without explicit geometry or depth maps. This makes it especially robust with thin structures and transparencies. Try the demo below: 🌐 Project: https://hf.co/spaces/prs-eth/stereospace_web 📕 Paper: https://hf.co/papers/2512.10959 🐙 Code: https://github.com/prs-eth/stereospace 🤗 Demo: https://hf.co/spaces/toshas/stereospace 🤗 Weights: https://hf.co/prs-eth/stereospace-v1-0 By ETH Zürich (@behretj, @Bingxin, @konradschindler), University of Bologna (@fabiotosi92, @mpoggi), HUAWEI Bayer Lab (@toshas).

liked a Space about 18 hours ago

toshas/stereospace

posted an update about 18 hours ago

View all activity

Organizations

Posts 7

Post

149

Introducing StereoSpace -- our new end-to-end method for turning photos into stereo images without explicit geometry or depth maps. This makes it especially robust with thin structures and transparencies. Try the demo below:

🌐 Project: prs-eth/stereospace_web
📕 Paper: StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space (2512.10959)
🐙 Code: https://github.com/prs-eth/stereospace
🤗 Demo: toshas/stereospace
🤗 Weights: prs-eth/stereospace-v1-0

By ETH Zürich ( @behretj , @Bingxin , @konradschindler ), University of Bologna ( @fabiotosi92 , @mpoggi ), HUAWEI Bayer Lab ( @toshas ).

Post

2107

Introducing 🇨🇭WindowSeat🇨🇭 –– 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:
🤗 toshas/windowseat-reflection-removal

Other resources:
🌎 Website: huawei-bayerlab/windowseat-reflection-removal-web
🎓 Paper: Reflection Removal through Efficient Adaptation of Diffusion Transformers (2512.05000)
🤗 Model: huawei-bayerlab/windowseat-reflection-removal-v1-0
🐙 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

View all Posts