facebookresearch/map-anything
Regress metric 3D geometry from images via transformers
View on index · View in 3D Map
Related repos
- Generates 3D meshes from image sequences and SLAM points
- Model for reconstruction of 3D objects from images
- Reconstructs 3D scenes from 1000+ images in one forward pass
- VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
- Model for recovery of human mesh from images
- Generates animated 3D meshes from videos
- data augmentations for audio, image, text, and video
- tracks any pixel in video with transformer-based model, supports dense and long-term point tracking even through occlusion
- segment anything in images and videos with sam2
- video and image watermarking code for training and inference
