facebookresearch/sam2

segment anything in images and videos with sam2

video and image watermarking code for training and inference
facebookresearch/videoseal
EdgeTAM: on-device SAM 2 variant for segmentation and tracking in videos, runs faster, processes 16 FPS on iPhone 15 Pro Max
facebookresearch/EdgeTAM
data augmentations for audio, image, text, and video
facebookresearch/AugLy
State-of-the-art object detection and segmentation library from Facebook AI Research
facebookresearch/detectron2
Video models like SlowFast help computers spot actions and understand what’s happening in videos by combining slow and fast motion cues
facebookresearch/SlowFast
AI model for cutting out objects from images with simple prompts
facebookresearch/segment-anything
turns audio into realistic talking avatars
facebookresearch/audio2photoreal
tracks any pixel in video with transformer-based model, supports dense and long-term point tracking even through occlusion
facebookresearch/co-tracker
library for finding similar vectors and clustering data
facebookresearch/faiss
VGGT is a neural network that predicts 3D scene attributes like camera parameters, depth, and point maps from images
facebookresearch/vggt