A collection of YOLO object detection models fine-tuned on the Brackish benchmark for underwater marine animal detection. RF-DETR variants to follow.
🤝 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
repliedto their post about 3 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 4 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). new activity about 9 hours ago
dronefreak/histoformer-weather-restoration:Upload requirements.txtOrganizations
A collection of YOLO and RF-DETR object detection models fine-tuned on the GWHD benchmark for wheat head detection in agricultural images.
A collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation on Aeroscapes dataset.
-
dronefreak/aeroscapes-yolo26m-sem
Image Segmentation • Updated • 25 • 2 -
dronefreak/aeroscapes-yolo26x-sem
Image Segmentation • Updated • 25 • 3 -
dronefreak/aeroscapes-cabinet-mobilenetv3-large
Image Segmentation • Updated • 12 • 2 -
dronefreak/aeroscapes-yolo26l-sem
Image Segmentation • Updated • 32 • 2
A collection of YOLO/RF-DETR models trained and evaluated under a common pipeline for AD traffic light detection on LISA Traffic Lights dataset.
A collection of YOLO-based object detection models fine-tuned on the VisDrone benchmark for aerial imagery.
A collection of YOLO and RF-DETR object detection models fine-tuned on the SeaDronesSee benchmark Maritime UAV Object Detection Dataset.
A collection of YOLO and RF-DETR object detection models fine-tuned on the Extra Dark benchmark for object detection in night time images.
A collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation on VDD 2025 dataset.
A collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation.
A collection of YOLO object detection models fine-tuned on the Brackish benchmark for underwater marine animal detection. RF-DETR variants to follow.
A collection of YOLO and RF-DETR object detection models fine-tuned on the SeaDronesSee benchmark Maritime UAV Object Detection Dataset.
A collection of YOLO and RF-DETR object detection models fine-tuned on the GWHD benchmark for wheat head detection in agricultural images.
A collection of YOLO and RF-DETR object detection models fine-tuned on the Extra Dark benchmark for object detection in night time images.
A collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation on Aeroscapes dataset.
-
dronefreak/aeroscapes-yolo26m-sem
Image Segmentation • Updated • 25 • 2 -
dronefreak/aeroscapes-yolo26x-sem
Image Segmentation • Updated • 25 • 3 -
dronefreak/aeroscapes-cabinet-mobilenetv3-large
Image Segmentation • Updated • 12 • 2 -
dronefreak/aeroscapes-yolo26l-sem
Image Segmentation • Updated • 32 • 2
A collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation on VDD 2025 dataset.
A collection of YOLO/RF-DETR models trained and evaluated under a common pipeline for AD traffic light detection on LISA Traffic Lights dataset.
A collection of CABiNet and YOLO26 models trained and evaluated under a common pipeline for aerial semantic segmentation.
A collection of YOLO-based object detection models fine-tuned on the VisDrone benchmark for aerial imagery.