CanopyRS 🌴

CanopyRS (Canopy Remote Sensing) is a pipeline designed for processing high-resolution geospatial orthomosaics to detect, segment, and (in the future) classify trees of various forest biomes. It supports state-of-the-art model architectures spanning both CNNs (Faster R-CNN, Mask R-CNN, RetinaNet) and transformers (DINO, Mask2Former, SAM 2, SAM 3).

The datasets hosted here are used to train and benchmark models in CanopyRS, and the model checkpoints hosted here can be run directly through the CanopyRS pipeline.

• 💻 Code: CanopyRS on GitHub
• 📖 Documentation: hugobaudchon.github.io/CanopyRS
• 📄 Paper: SelvaBox — ICLR 2026 · arXiv:2507.00170
• ▶️ Try it: Google Colab tutorial