Repository Showcase
A curated collection of interesting GitHub repositories
facebookresearch/vggt
VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
Related repos
- PyTorch models for high-res vision tasks using self-supervised learning
- 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
- Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
- data augmentations for audio, image, text, and video
- State-of-the-art object detection and segmentation library from Facebook AI Research
- Open vision-language models that compete with closed-source alternatives using fully open data
- dense SLAM with neural implicit encoding for indoor scenes
- Detects any keypoints on images
- segment anything in images and videos with sam2
