facebookresearch/SlowFast
Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
View on index · View in 3D Map
Related repos
- Library for video understanding research
- video and image watermarking code for training and inference
- tracks any pixel in video with transformer-based model, supports dense and long-term point tracking even through occlusion
- EdgeTAM: on-device SAM 2 variant for segmentation and tracking in videos, runs faster, processes 16 FPS on iPhone 15 Pro Max
- Reconstructs 3D scenes from 1000+ images in one forward pass
- data augmentations for audio, image, text, and video
- PyTorch models for high-res vision tasks using self-supervised learning
- segment anything in images and videos with sam2
- VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
- Analyzes videos using vision models and Whisper
