Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/79464
Title: BEAUTY AS AMPLIFIED PERCEPTION : AUTOMATIC ARTIST-LEVEL LIGHT MONTAGE
Authors: VLAD HOSU
Keywords: computational photography, computational aesthetics, light montage, lighting design, image enhancement, amplified perception
Issue Date: 26-Mar-2014
Source: VLAD HOSU (2014-03-26). BEAUTY AS AMPLIFIED PERCEPTION : AUTOMATIC ARTIST-LEVEL LIGHT MONTAGE. ScholarBank@NUS Repository.
Abstract: What separates great photos from commonplace snapshots? Is it their elusive beauty or something else altogether? Perceptual fluency, the human visual system's ability to interpret images holds the answer. Professional photographers use light to express object form and shape. They create beautiful works of art from ordinary objects. What if we could do the same automatically? We introduce amplified perception, a theory describing how to systematically enhance images. The proposed techniques create light montages from photos in multiple illuminations. These compositions augment the depiction of shape by emphasizing visual cues such as shading, reflections and textures. They lean on neuro-aesthetics to render beautiful, photo realistic montages. The results are evaluated by conducting extensive surveys. Our techniques consistently outperform previous methods, surpassing the works of a professional Adobe Photoshop artist. We discuss implications for future research and applications.
URI: http://scholarbank.nus.edu.sg/handle/10635/79464
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
HosuV.pdf17.59 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

139
checked on Feb 16, 2018

Download(s)

39
checked on Feb 16, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.