Instance segmentation for cartoon/anime characters and some visual techniques building around it.
-
Updated
Apr 29, 2025 - Jupyter Notebook
Instance segmentation for cartoon/anime characters and some visual techniques building around it.
Rendering Realistic Bokeh Images with PyNET
[ICLR2026] Any-to-Bokeh is a novel one-step video bokeh framework that converts arbitrary input videos into temporally coherent, depth-aware bokeh effects.
An implementation note for "Hexagonal Bokeh Blur Filter" in MetalPetal.
[ICCV 2025 Highlight] Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures. Official Code and Dataset
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.
An immersive 3D neural network experience featuring dynamic particle systems, glowing neural pathways, and atmospheric post-processing effects. Built with Three.js and custom GLSL shaders.
GIMP plugin that add the ability to perform a lens blur, also known as Bokeh blur
Implementing Portrait Mode, Background Blur or Bokeh Effect using Tensorflow.
Vue component that ask for user media stream and blurs or mask persons backgrounds with artificial intelligence using tensorflowjs and the body-pix api
Background substitution from an image/video using FCN image segmentation
GSAP Background Bokeh Animation. No plugins are required
CUDA implementations of various Computer Vision Algorithms
✨ Enhance portrait images from casual captures to professional quality with advanced techniques for lighting and subject refinement.
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.
📸 Enhance raw human portraits into studio-quality images with a multi-stage pipeline for improved lighting and subject detail.
Add a description, image, and links to the bokeh-effect topic page so that developers can more easily learn about it.
To associate your repository with the bokeh-effect topic, visit your repo's landing page and select "manage topics."