An implementation of the ICCP '16 paper "Blind Dehazing Using Internal Patch Recurrence". Colorizing. We introduce a deep neural network (DNN) architecture that uses the dual-pixel (DP) sub-aperture views to reduce defocus blur. computational-photography small objects detection and tracking, vision theory. texture synthesis Blending two images photorealistically using graphcuts, Microshift Compression: An Efficient Image Compression Algorithm for Hardware. Seam Carving and Lightfield Camera. Machine Learning . This class explores how computation impacts the entire workflow of photography, which is traditionally aimed at capturing light from a (3D) scene to form a (2D) image. Any user of this system must comply with all Institute and Board of Regents policies, including the Acceptable Use Policy, Cyber Security Policy and Data Privacy Policy ( Specifically, I am interested in Vision and Language, 3D vision, Neural Rendering, Computational photography, Image & Video Understanding, AR/VR & Embodied AI. We use optional third-party analytics cookies to understand how you use so we can build better products. To associate your repository with the Create high resolution astrophotography with your smartphone. By using this system, I acknowledge and consent to these terms. We use essential cookies to perform essential website functions, e.g. computational_photography_final_project. The most recent code on github at 11:59pm on the due date is the code we will grade. Reference github repository for the paper "Defocus Deblurring Using Dual-Pixel Data". I am actively working with deep neural networks for videos and image sequences. However, utilising a technique from computational photography called coded aperture, we can obtain absolute depth using just a single image.The idea in coded aperture is similar … I am a research fellow in the Rapid-Rich Object Search Lab of Nanyang Technological University.Before than, I obtained my Ph.D. degree from NTU in 2019 supervised by Prof. Alex C. Kot, Prof. Tan Ah Hwee, and Prof. Boxin Shi and my bachelor degree from the University of Electronic Science and Technology of China in 2012.. wanpeoplejie[at] Our method is a coarse-to-fine deep learning model to correct badly-exposed photographs. # Computational Photography (ICCP), 2014 IEEE International Conference on # # hL and hH are the one dimenionsal filters designed by our optimization # bL and bH are the corresponding Chebysheve polynomials # t is the 3x3 McClellan transform matrix # directL and directH are the direct forms of the 2d filters My experience with Georgia Tech's OMSCS Published on December 20, 2016 December 20, 2016 • 434 Likes • 57 Comments I obtained my Ph.D. in computer science from Northwestern University, where I worked on computational photography and computer vision with Oliver Cossairt in Computational Photography Lab . ATTENTION: When you are finished using all of your authenticated applications, please log out of this system and exit your browser to ensure you do not leave any of your applications (such as your e-mail) open to other users of this machine. The most recent submission in Canvas at that point, is the one we grade. We would like to show you a description here but the site won’t allow us. A collection of important assignment projects from MOOCs completed on edX and Coursera. Learn more. Soham Ghormade. My research interest stems from my deep fascination with upcyling. This is the implementation for Deep High Dynamic Range Imaging with Large Foreground Motions (ECCV'18), 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, White balance camera-rendered sRGB images (CVPR 2019) [Matlab & Python], Code for CVPR 2020 paper "Deep Local Parametric Filters for Image Enhancement". My Ph.D. thesis was closely related to the tasks which involve moving objects present in videos or images captured from different view-points. This repo contains lecture notes and codes for Computational Photography course on Udacity. Optical Society of America, 2017. I work for a part of the National Major Project of Scientific Instrument, called Multi-dimensional and Multi-scale High-resolution Computational Photography Instrument. The camera parameter could be aperture, exposure, focus, film speed or viewpoint. Learn more. Sign up. We use optional third-party analytics cookies to understand how you use so we can build better products. Personal portfolio powered by Jekyll and GitHub Pages . Filters and Frequencies. I also enjoy hiking, photography, speed cubing and picking up random skills. I started my research work in computational optics & computational imaging since I was a senior in Tsinghua University. GitHub no longer supports this web browser. I was a research intern at MSRA, supervised by Dr. Xun Guo. GitHub is where people build software. Master's project implementing depth estimation for spherical images using unsupervised learning with CNNs. More than 50 million people use GitHub to discover, fork, and contribute to over 100 million projects. Before joining Georgia Tech, I was the Manning Assistant Professor of Computer Science at Brown University. This iteration of the class makes use of material from the classes by James Tompkin, Ioannis Gkioulekas, Marc Pollefeys, and Alyosha Efros. Wenqi Xian. My research includes Deep Learning applied to Computer Graphics, Computational Photography and Computer Vision.