There are 1 repository under depth-of-field topic.
Reference github repository for the paper "Defocus Deblurring Using Dual-Pixel Data". We introduce a deep neural network (DNN) architecture that uses the dual-pixel (DP) sub-aperture views to reduce defocus blur.
Graphics engine written in C++ using DirectX11
Package for taking gameplay screenshots in the Unity Editor across all three pipeline types
Reference github repository for the paper "Learning to Reduce Defocus Blur by Realistically Modeling Dual-Pixel Data". We propose a procedure to generate realistic DP data synthetically. Our synthesis approach mimics the optical image formation found on DP sensors and can be applied to virtual scenes rendered with standard computer software. Leveraging these realistic synthetic DP images, we introduce a new recurrent convolutional network (RCN) architecture that can improve defocus deblurring results and is suitable for use with single-frame and multi-frame data captured by DP sensors.
Reference github repository for the paper "Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning". We propose a single-image deblurring network that incorporates the two sub-aperture views into a multitask framework. Specifically, we show that jointly learning to predict the two DP views from a single blurry input image improves the network’s ability to learn to deblur the image. Our experiments show this multi-task strategy achieves +1dB PSNR improvement over state-of-the-art defocus deblurring methods. In addition, our multi-task framework allows accurate DP-view synthesis (e.g., ~ 39dB PSNR) from the single input image. These high-quality DP views can be used for other DP-based applications, such as reflection removal. As part of this effort, we have captured a new dataset of 7,059 high-quality images to support our training for the DP-view synthesis task.
Extract the EDOF from photos obtained from Dual Camera smartphones
DirectX 12 Rendering Engine
depth of field utilities
Official Repository for our CVPRW (MAI'21) paper.
A Physically Based Vulkan Renderer.
A Windows only OpenGL 4.6 renderer for testing different rendering techniques & solutions.
A mobile implementation of depth of field.
Personal test project to experiment with Unity 2019.4.11f URP (Universal Rendering Pipeline), Shadergraph, scripted Depth of focus, and plane generation.
Rendering 3D scenes with geometric figures, mirrors, realistic shadows, depth of field and global illumination.
investigating generative approaches to simulating depth of field in images
Path tracer written in JS
Implementation of a CVPR2020 paper using Plenpy for the 15-663 Computational Photography course at Carnegie Mellon University
Go Programming Language | Golang Examples | Example Codes | Concepts | Online Resources
Rendering Engine in DirectX 11
OpenGL renderer using a realistic camera model
Simple Ray Tracer made with C++ 17 and GLM
C++ multi-threaded raytracer experiment with anti aliasing, motion blur, depth of field and other features
C# Raytracer with GLB file format reader (WIP)
An experimental scene graph and depth of field post processor using WebGL.
Yet another ray tracer based on Blinn-Phong reflection model.