CLIP + FFT/DWT/RGB = text to image/video
CoTracker is a model for tracking any point (pixel) on a video
Visual localization made easy with hloc
A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator
PaddlePaddle GAN library, including lots of interesting applications
The official pytorch implementation of our paper
A real-time approach for mapping all human pixels of 2D RGB images
We estimate dense, flicker-free, geometrically consistent depth
Efficient 3D human pose estimation in video using 2D keypoint