Corpus-based Visual Synthesis: An Approach to Artistic Stylization P - PowerPoint PPT Presentation

Corpus Images Source Image Stylization Corpus-based Visual Synthesis: An Approach to Artistic Stylization P a r a g K . M i t a l 1 M i c k G r i e r s o n 1 T i m S m i t h 2 1 Department of Computing , Goldsmit hs, University of London 2 Department of Psychological Sciences , Bir k b e ck , University of London A C M S y m p o s i u m O n A p p l i e d P e r c e p t i o n | 2 3 A u g u s t 2 0 1 3

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 2 / 71 ✤ Perception must be supported by pre- Representation attentive representations ✤ Abstract description of objects/scenes ✤ Numerous theories: ✤ Gestalts ✤ Geons (Biederman) ✤ Object files (Wolfe) ✤ Proto-objects (Rensink) ✤ Indexicals (Pylyshyn) ✤ Shapes (Marr) ✤ Streams (Bregman)

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 8 / 71 ✤ Artists are well aware of the role of Representation abstract representations in perception ✤ Influence how we look at and where we look in a scene ✤ Art Movements ✤ Impressionism ✤ Pointilism ✤ Cubism ✤ Orphism ✤ Expressionism ✤ Abstract-Expressionism

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 15 / 71 Related Work ✤ Filtering/Clustering ✤ Example-based Images ✤ Texture-transfer/Patch-based ✤ Dictionary methods/Collage approaches Kyprianidis, J. et al., 2012. State of the “Art”: A Taxonomy of Artistic Stylization Techniques for Images and Video. IEEE transactions on Visualization and Computer Graphics . Available at: http://ieeexplore.ieee.org/xpls/abs_all.jsp? arnumber=6243138

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 16 / 71 Problem Statement ✤ Create automated artistic ✤ Our approach stylizations of images/videos ✤ Build corpus of abstract representations using an understanding of the from user chosen images role of abstract representations in art and perception ✤ Match target image’s abstract representations to nearest ones in corpus ✤ Allow for a range of styles through a simple set of ✤ Synthesize target image using closest parameters matches ✤ Interact with a simple set of parameters ✤ Needs to be fast in order to effecting representation detection and explore different styles synthesis quickly / run in real-time

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 17 / 71 Outline ✤ CBVS Framework ✤ Results for Images/Videos ✤ Extensions ✤ Memory Mosaicing ✤ Augmented Reality Hallucinations ✤ PhotoSynthesizer (iOS app) ✤ Conclusion

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 18 / 71 Outline ✤ CBVS Framework ✤ Results for Images/Videos ✤ Extensions ✤ Memory Mosaicing ✤ Augmented Reality Hallucinations ✤ PhotoSynthesizer (iOS app) ✤ Conclusion

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 19 / 71 CBVS Framework ✤ Build corpus of abstract representations from user chosen images ✤ Match target image’s abstract representations to nearest ones in corpus R C = { R 1 , R 2 , ..., R N C } ✤ Synthesize target image using closest matches ✤ Interact with a simple set of parameters effecting representation detection and synthesis

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 20 / 71 Build ing the Corpus ✤ Need to represent: ✤ Sparse/Dense strokes ✤ Small/Large strokes ✤ Watershed? ✤ Posterization? ✤ Mean-Shift?

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 21 / 71 Build ing the Corpus ✤ Maximally Stable Color Regions ✤ No need for multiple scale detections ✤ Implicit ordering of regions ✤ Simple set of parameters for discovering sparse/dense small/ large strokes ✤ Fast/Robust across multiple views (used in video tracking) ✤ Similar process to the unconscious representations as theorized before

Corpus-based Visual Synthesis: An Approach to Artistic Stylization | Parag K. Mital | http://pkmital.com 22 / 71

Corpus-based Visual Synthesis: An Approach to Artistic Stylization P - PowerPoint PPT Presentation

Corpus Images Source Image Stylization Corpus-based Visual Synthesis: An Approach to Artistic Stylization P a r a g K . M i t a l 1 M i c k G r i e r s o n 1 T i m S m i t h 2 1 Department of Computing , Goldsmit hs, University of London 2

TOWARD A NON-VISUAL IMAGE (an artistic approach) Olivier Perriquet IMAGE IS AN AMBIGUOUS CONCEPT

The Game Development Process Artistic Content Creation New Artistic Courses AR 1100.

The Game Development Process Audio Visual Design and Production New Artistic Courses AR

The Game Development Process Visual Design and Production New Artistic Courses AR 1100.

A template-based approach for speech synthesis intonation generation using LSTMs Srikanth Ronanki

Hierarchy-of-Visual-Words: a Learning-based Approach for Trademark Image Retrieval Vtor

Dialogic units in spoken Brazilian and Italian: A corpus based approach Maryual M. MITTMANN;

A Corpus of Natural Language for Visual Reasoning Cornell Natural Language Visual Reasoning

Art Artistic ic Imp mpressio ion Onl Only Art Artistic ic Imp mpressio ion Onl Only No

Visual Litter Surveys Where we came from where we are now and a new approach to Visual Litter

An Approach to Synthesis of An Approach to Synthesis of Multiple-Valued Reversible

Manipulation and Synthesis Jun-Yan Zhu UC Berkeley 2017/01/11 @ VALSE What is visual

ERROR ANALYSIS IN A WRITTEN LEARNER CORPUS FROM SPANISH SPEAKERS EFL LEARNERS. A CORPUS BASED

Independent Parallel Runway Visual Approach in Beijing Capital Airport SUMMARY Basic

Is there a new infinitive in Russian Romani?: a corpus-based study of subject-verb agreement

An Alterna)ve Approach to Hardware Benchmarking of CAESAR Candidates Based on the Use of

Ethics in A YOUNG PROFESSION Computing COPING WITH ETHICAL DEBT Theo Schlossnagle @POSTWAIT

A Genetic Algorithm to Improve Linux Kernel Performance on Resource-Constrained Devices James T.

AECOM June 2017 KUALA LUMPUR-SINGAPORE HIGH SPEED RAIL Singapore Providing complete design

EASO Consultative Forum Synergies with civil society in the relocation process: the experience of

Colorado River Basin Water Supply and Demand Study Public Outreach Meeting July 17, 2012

ACM 2018 Bill Hightower Hope. Faith. Love. FAITH Because of the increase of wickedness,..

Q3 2018 Results The Hague, 5 November 2018 Q3 2018 Results Nexive and Postcon are classified as

Incoop: MapReduce for Incremental Computations Bhatotia, P., Wieder, A., Rodrigues, R., Acar,