facebookresearch/momentum
Generates realistic human motion via kinematic optimization
View on index · View in 3D Map
Related repos
- Physics-informed human-to-robot motion retargeting
- Generates 3D meshes from image sequences and SLAM points
- Generates realistic human motion from text prompts
- Generates animated 3D meshes from videos
- Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
- Reconstructs 3D scenes from 1000 images in one forward pass
- Library for object detection and segmentation
- VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
- Vision foundation models for dense features
- Benchmark for agents to reproduce scientific findings
