An Interactive Editing Tool for Correcting Panoramas

Constructing panoramas from an image series is a fundamental task for photo-editing.In this paper,we introduce a simple, but effective interactive tool for correcting panoramas. In particular, we describe two features: 1) a seam-editing tool that allows the user to modify blending seams in a local manner; and 2) a content-aware snapping tool to help the user better align local image content between overlapping images.
We demonstrate the effectiveness of our tool on several examples that are tedious to achieve using existing photo-editing softwares.

Junhong Gao, National University of Singapore
Michael Brown, National University of Singapore

Asset Digitization: Moving Beyond Facsimile

Digitization as data collection enables new possibilities in digital restoration, context-preserving language translation, detection of change over time, and the construction of high-level narratives that provide a compelling
interpretive framework. We show examples, and while facsimile remains an important by-product, we
encourage a shift in the mindset of conservators, curators, and digitization teams.

W. Brent Seales, University of Kentucky
Steve Crossan, Google Cultural Institute

Image-based Clothes Animation for Virtual Fitting

We propose an image-based approach for virtual clothes fitting, in which a user moves freely in front of a virtual mirror (i.e., video screen) that displays the user wearing a superimposed virtual garment. The motions and deformations of the virtual garment are synthesized by tracking the user’s skeleton and utilizing corresponding video clips of the actual garment worn by a model.

Zhenglong Zhou, National University of Singapore
Bo Shu, National University of Singapore
Shaojie Zhuo, National University of Singapore
Xiaoming Deng, National University of Singapore
Ping Tan, National University of Singapore
Stephen Lin, Microsoft Research Asia

Real-time Contrast Preserving Decolorization

We propose a real-time contrast preserving decolorization method. The main contributions include a bimodal objective function with a linear grayscale model, a fast non-iterative optimization, and a sampling based acceleration.
The effectiveness of the proposed model has been borne out by quantitative comparison using a novel CCPR metric.

Cewu Lu, The Chinese University of Hong Kong
Li Xu, The Chinese University of Hong Kong
Jiaya Jia, The Chinese University of Hong Kong

Image Memorability and Visual Inception

Aditya Khosla, Massachusetts Institute of Technology
Jianxiong Xiao, Massachusetts Institute of Technology
Phillip Isola, Massachusetts Institute of Technology
Antonio Torralba, Massachusetts Institute of Technology
Aude Oliva, Massachusetts Institute of Technology