dronefreak/Rain13K
Viewer • Updated • 36k • 1.17k • 3
🤝 Open to Collab
Saumya Saksena
dronefreak
AI & ML interests
Computer Vision, Deep Learning, Image Restoration, Image De-noising, LLMs, RAG, Image Classification, Image Segmentation, EEG Classification, Signal Processing, PPG, BCI
Recent Activity
liked a Space about 7 hours ago
cinderholm/wan-i2v repliedto their post about 20 hours ago
🌧️❄️ Free demo: remove rain, raindrops, or snow from a photo with a single model
I put together an unofficial demo for **Histoformer** (ECCV 2024, arXiv: 2407.10172), a 16.6M-parameter transformer that handles three different weather degradations, rain streaks, adherent raindrops, and snow, in one unified model. It uses a "histogram self-attention" mechanism that groups pixels by degradation intensity instead of spatial position, which is a
neat way to sidestep the usual spatial-window tradeoffs in restoration transformers.
Try it here, free on ZeroGPU: https://huggingface.co/spaces/dronefreak/histoformer-weather-restoration
Upload a photo and get a before/after slider. Two checkpoints available: one tuned for real-world photos, one for the paper's synthetic benchmarks.
Also put together a cleaner, easy-to-use model card with a copy-pasteable Quickstart if you'd rather run it yourself: https://huggingface.co/dronefreak/Histoformer
This is an unofficial demo/mirror, not affiliated with the original authors. All credit for the actual research goes to Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, and Xiaochun Cao (@sunsean). Official repo: https://github.com/sunshangquan/Histoformer. Weights are MIT-licensed.
Reported numbers from the paper: 32.1 PSNR on rain+fog (Outdoor-Rain), 33.1 on raindrops, 37.4 / 32.2 on light/heavy snow (Snow100K-S/L). posted an update about 22 hours ago
🌧️❄️ Free demo: remove rain, raindrops, or snow from a photo with a single model
I put together an unofficial demo for **Histoformer** (ECCV 2024, arXiv: 2407.10172), a 16.6M-parameter transformer that handles three different weather degradations, rain streaks, adherent raindrops, and snow, in one unified model. It uses a "histogram self-attention" mechanism that groups pixels by degradation intensity instead of spatial position, which is a
neat way to sidestep the usual spatial-window tradeoffs in restoration transformers.
Try it here, free on ZeroGPU: https://huggingface.co/spaces/dronefreak/histoformer-weather-restoration
Upload a photo and get a before/after slider. Two checkpoints available: one tuned for real-world photos, one for the paper's synthetic benchmarks.
Also put together a cleaner, easy-to-use model card with a copy-pasteable Quickstart if you'd rather run it yourself: https://huggingface.co/dronefreak/Histoformer
This is an unofficial demo/mirror, not affiliated with the original authors. All credit for the actual research goes to Shangquan Sun, Wenqi Ren, Xinwei Gao, Rui Wang, and Xiaochun Cao (@sunsean). Official repo: https://github.com/sunshangquan/Histoformer. Weights are MIT-licensed.
Reported numbers from the paper: 32.1 PSNR on rain+fog (Outdoor-Rain), 33.1 on raindrops, 37.4 / 32.2 on light/heavy snow (Snow100K-S/L).Organizations
