root

Back in March, we open-sourced our implementation of “Fast Dense Feature Extraction with CNN’s that have Pooling or Striding Layers”, Although not broadly known, The 2017… Read More »Speedup your CNN using Fast Dense Feature Extraction and PyTorch

Image restoration with neural networks without learning Deep learning requires a large amount of data. This phrase has become popular among people who consider applying deep… Read More »How To Perform Image Restoration Absolutely DataSet Free

Taking into consideration the uniqueness of Human In recent years, research related to “humans” in the computer vision community has become increasingly active because of… Read More »Detection Free Human Instance Segmentation using Pose2Seg and PyTorch

Photo-realistic re-animation of portrait videos using only an input video Synthesizing and editing video portraits—i.e., videos framed to show a person’s head and upper body—is… Read More »Deep Video Portraits

End-to-end Hand Mesh Recovery from a Monocular RGB Image. In recent years, research related to vision-based 3D image processing has become increasingly active, given its… Read More »HAMR — 3D Hand Shape and Pose Estimation from a Single RGB Image

End-to-End Self-Supervised Learning for Active Stereo Systems Depth sensing is a classic problem with a long history of prior work. It’s at the heart of… Read More »ActiveStereoNet: The first deep learning solution for active stereo systems

Unsupervised Image Decomposition via Coupled Deep-Image-Priors Many computer vision tasks aspire to decompose an image into its sole components. In Image segmentation, the image is… Read More »Why you should Double-DIP for Natural Image Decomposition