Marigold Intrinsic Image Decomposition
π΅
25
Extract albedo, shading, and material maps from a photo
Anton Obukhov PRO
toshas
AI & ML interests
Generative Computer Vision
Recent Activity
updated a Space about 10 hours ago
prs-eth/marigold-intrinsics updated a Space about 10 hours ago
prs-eth/marigold updated a Space about 10 hours ago
prs-eth/marigold-normalsOrganizations
updated 3
Spaces about 10 hours ago
liked a
Space 21 days ago
updated a
Space 3 months ago
liked a
model 4 months ago
reacted to their post with π₯ 5 months ago
Post
2375
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
Add Huggingface Space Header
#1 opened 7 months ago
by 
blanchon
liked a
Space 8 months ago
upvoted a paper 8 months ago
reacted to their post with π 8 months ago
Post
922
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:
π Project: https://hf.co/spaces/prs-eth/stereospace_web
π Paper: StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space (2512.10959)
π Code: https://github.com/prs-eth/stereospace
π€ Demo: toshas/stereospace
π€ Weights: prs-eth/stereospace-v1-0
By ETH ZΓΌrich (@behretj , @Bingxin , @konradschindler ), University of Bologna (@fabiotosi92 , @mpoggi ), HUAWEI Bayer Lab (@toshas ).
π Project: https://hf.co/spaces/prs-eth/stereospace_web
π Paper: StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space (2512.10959)
π Code: https://github.com/prs-eth/stereospace
π€ Demo: toshas/stereospace
π€ Weights: prs-eth/stereospace-v1-0
By ETH ZΓΌrich (@behretj , @Bingxin , @konradschindler ), University of Bologna (@fabiotosi92 , @mpoggi ), HUAWEI Bayer Lab (@toshas ).
liked a
Space 8 months ago
posted an update 8 months ago
Post
922
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:
π Project: https://hf.co/spaces/prs-eth/stereospace_web
π Paper: StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space (2512.10959)
π Code: https://github.com/prs-eth/stereospace
π€ Demo: toshas/stereospace
π€ Weights: prs-eth/stereospace-v1-0
By ETH ZΓΌrich (@behretj , @Bingxin , @konradschindler ), University of Bologna (@fabiotosi92 , @mpoggi ), HUAWEI Bayer Lab (@toshas ).
π Project: https://hf.co/spaces/prs-eth/stereospace_web
π Paper: StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space (2512.10959)
π Code: https://github.com/prs-eth/stereospace
π€ Demo: toshas/stereospace
π€ Weights: prs-eth/stereospace-v1-0
By ETH ZΓΌrich (@behretj , @Bingxin , @konradschindler ), University of Bologna (@fabiotosi92 , @mpoggi ), HUAWEI Bayer Lab (@toshas ).
updated a
collection 8 months ago
published a
Space 8 months ago
updated a
Space 8 months ago
authored a
paper 8 months ago
liked a
model 8 months ago
liked a
Space 8 months ago
upvoted a collection 8 months ago