Rendering Realistic Bokeh Images with PyNET

Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.

Official Pytorch implementation of ICCV 2021 2020 paper "Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision"

Official Repository for our CVPRW (MAI'21) paper.

GIMP plugin that add the ability to perform a lens blur, also known as Bokeh blur

Background substitution from an image/video using FCN image segmentation

This project implements a comprehensive computer vision pipeline for elevating raw human portrait photography to studio-quality standards. It integrates several advanced image processing techniques such as CLAHE in LAB color space, bilateral filtering, masked gaussian blurring etc.