facebookresearch/ShapeR

Generates 3D meshes from image sequences and SLAM points

View on index · View in 3D Map

Related repos

• Generates animated 3D meshes from videos
• Reconstructs 3D scenes from 1000+ images in one forward pass
• Model for reconstruction of 3D objects from images
• Model for recovery of human mesh from images
• VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
• tracks any pixel in video with transformer-based model, supports dense and long-term point tracking even through occlusion
• PyTorch models for high-res vision tasks using self-supervised learning
• Library for object detection and segmentation
• Tool for turning hand-drawn characters into simple animations using AI
• Generates a 3D mesh from a single image