Results 21 to 30 of about 208,882 (239)

Cross-Domain Face Sketch Synthesis

open access: yesIEEE Access, 2019
Synthesizing sketches from facial photos is of great significance to digital entertainment. Along with higher demands on sketch quality in a complex environment, however, it has been an urgent issue on how to synthesize realistic sketches with the ...
Mingjin Zhang   +5 more
doaj   +1 more source

A Joint Training Model for Face Sketch Synthesis

open access: yesApplied Sciences, 2019
The exemplar-based method is most frequently used in face sketch synthesis because of its efficiency in representing the nonlinear mapping between face photos and sketches.
Weiguo Wan, Hyo Jong Lee
doaj   +1 more source

Autonomous exploration using UWB and LiDAR

open access: yesJournal of Automation and Intelligence, 2023
In autonomous exploration, a robot navigates itself in an unknown environment while building a 2D map of the environment. This is typically done using a LiDAR sensor, which however is susceptible to error accumulation.
Mingyang Guan, Changyun Wen
doaj   +1 more source

Sketch-based virtual human modelling and animation [PDF]

open access: yes, 2007
Animated virtual humans created by skilled artists play a remarkable role in today’s public entertainment. However, ordinary users are still treated as audiences due to the lack of appropriate expertise, equipment, and computer skills. We developed a new
Mao, C, Qin, S F, Wright, D
core   +2 more sources

2D Image Deformation Based on Guaranteed Feature Correspondence and Mesh Mapping

open access: yesIEEE Access, 2019
Image deformation has ubiquitous usage in multimedia applications. It morphs one image into another through a seamless transition. Existing techniques either mainly focus on the correspondence mapping of interior features of the objects in two images ...
Yaqiong Liu   +3 more
doaj   +1 more source

Face Sketch Matching via Coupled Deep Transform Learning

open access: yes, 2017
Face sketch to digital image matching is an important challenge of face recognition that involves matching across different domains. Current research efforts have primarily focused on extracting domain invariant representations or learning a mapping from
Majumdar, Angshul   +5 more
core   +1 more source

Concrete Poiētics

open access: yesArchitecture Image Studies Scientific Journal, 2020
This paper reports on an experimental drawing installation that is part of a sequence of art works radicalising architectural drawing: Drawing in the Expanded Field.
Simon Twose
doaj   +1 more source

Technical Note: Use of remote sensing for landslide studies in Europe [PDF]

open access: yesNatural Hazards and Earth System Sciences, 2013
Within the framework of FP7, an EU-funded SafeLand project, a questionnaire was prepared to collect information about the use of remote sensing for landslide study and to evaluate its actual application in landslide detection, mapping and monitoring. The
V. Tofani   +4 more
doaj   +1 more source

End-to-End Photo-Sketch Generation via Fully Convolutional Representation Learning

open access: yes, 2015
Sketch-based face recognition is an interesting task in vision and multimedia research, yet it is quite challenging due to the great difference between face photos and sketches.
Ding, Shengyong   +4 more
core   +1 more source

Cross-Paced Representation Learning with Partial Curricula for Sketch-based Image Retrieval [PDF]

open access: yes, 2018
In this paper we address the problem of learning robust cross-domain representations for sketch-based image retrieval (SBIR). While most SBIR approaches focus on extracting low- and mid-level descriptors for direct feature matching, recent works have ...
Alameda-Pineda, Xavier   +4 more
core   +3 more sources

Home - About - Disclaimer - Privacy