There are 39 repositories under computational-photography topic.
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets, using a differentiable photo editing model.
Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time
🤖🖌️ Generate photo-realistic textures based on source images or (soon) PBR materials. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Android Camera that uses Enhanced image processing
Reference code for the paper: Deep White-Balance Editing (CVPR 2020). Our method is a deep learning multi-task framework for white-balance editing.
Project page of the paper "Learning Multi-Scale Photo Exposure Correction" (CVPR 2021).
White balance camera-rendered sRGB images (CVPR 2019) [Matlab & Python]
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.
Demo code of the paper: "Deep Image Harmonization", Y.-H. Tsai, X. Shen, Z. Lin, K. Sunkavalli, X. Lu and M.-H. Yang, CVPR 2017
[ICCV 2021 (Oral Presentation)] Dual-Camera Super-Resolution with Aligned Attention Modules (RefSR)
Multiframe Image Deconvolution (ICCV17)
Handheld Multi-image Super-resolution [Wronski et al., SIGGRAPH19]. Non-official GPU-supported Python implementation.
Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)
A curated list of awesome resources for topics related to computational photography via deep learning, which mainly focuses on image alignment and stitching.
Exposure Fusion Technique
PyTorch & Matlab code for the paper: CIE XYZ Net: Unprocessing Images for Low-Level Computer Vision Tasks (TPAMI 2021).
[AAAI 2024] Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption (Low-light enhance / Exposure correction + NeRF)
Interactive light field renderer using dynamically reparameterized light fields.
Corrects perspective aberrations in wide-angle portraits. Implementation of the paper "Distortion-Free Wide-Angle Portraits on Camera Phones". Course project for 15-663 Computational Photography.
Master's project implementing depth estimation for spherical images using unsupervised learning with CNNs.
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.
colorize video using publicly available neural-networks
Local Relighting of Real Scenes
Microshift Compression: An Efficient Image Compression Algorithm for Hardware
Dolly zoom without a zoom lens
This is PyTorch-lightning implementation of "Fast Image Processing with Fully-Convolutional Networks" (https://arxiv.org/abs/1709.00643)
[CVPR 2024] Official Implementation of Learning to Remove Wrinkled Transparent Film with Polarized Prior
This repo contains lecture notes and codes for Computational Photography course on Udacity.
Official implementation of the paper "TreEnhance: A Tree Search Method For Low-Light Image Enhancement"