Archive

DGIF 2017

Generating Content-aware Perspective Videos for Comfortable 360° Video Watching

Abstract To watch 360˚ videos on normal two-dimensional (2D) displays, we not only need to select the specific region we want to watch (known as the viewpoint selection step) but also need to project the selected part of the 360˚ […]

  Read more

360° Panorama Image Processing

Abstract With the recent advent of 360° cameras, spherical panorama images are becoming more popular and widely available. In this talk, I will begin with my recent result on upright adjustment of 360° spherical panoramas. In a spherical panorama, alignment […]

  Read more

Recent Results in Image Deblurring

Abstract One goal in computational photography is to overcome limitations of traditional cameras such as blur. Blur, which is one of the most annoying artifacts in photographs, is caused by long exposure time or lens aberration. Deblurring is a problem […]

  Read more

Learning with Minimum Supervision for Semantic Segmentation

Abstract Semantic segmentation is a visual recognition task aiming to estimate pixel-level class labels in images. This problem has been recently handled by Deep Convolutional Neural Networks (DCNNs), and the state of the art based on DCNNs achieve impressive records […]

  Read more

Visual Manipulation of 3D Objects for Robotic Service

Abstract Visual manipulation relies on understanding the 3D workspace at hand by recognizing and localizing 3D objects embedded in the scene. For the sake of manipulation, it further requires understanding local geometric features and their context regarding the 3D object […]

  Read more

Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network

Abstract We present a novel deep learning framework that models the scene dependent image processing inside cameras. Often called as the radiometric calibration, the process of recovering RAW images from processed images (JPEG format in the sRGB color space) is […]

  Read more

Computational Media: from Processing to Creation of Media Contents

Abstract Computational media refers to the analysis and creation of media contents with computer algorithms, such as photos, videos, VR/AR experiences and music. It encompasses several disciplines such as computer vision, machine learning and multimedia. Exploring the complementarity of these […]

  Read more

A Personal Journey into Computational Photography: Past, Current and Future

Abstract In this talk, I’ll briefly review our past research efforts on computational photography and showcase a few technologies that have been successfully released in Adobe products. I’ll then present our current effort on using deep learning approaches to take […]

  Read more

CO and CO2 Activation at a Single Nickel Center

Abstract Adduct formations of the 1st row transition metals with small molecules such as carbon monoxide and carbon dioxide are drawing much attention due to their importance in developing synthetic catalysts for various industrial processes. In our laboratory, a series […]

  Read more

Toward Artificial Photosynthesis: Photocatalytic Water Oxidation and CO2 Reduction

Abstract As a strategy to confront energy and environmental problems, artificial photosynthesis has been intensively investigated worldwide including photocatalytic water splitting (O2 and H2 evolution) and CO2 reduction. We have developed an efficient photocatalytic water oxidation system using a bis(m-hydroxo) […]

  Read more