ECOA 2024 - Referências
Universidade Federal do Rio Grande do Sul (UFRGS)
Programa de Pós-Graduação em Computação (PPGC)
ECOA 2024
II Escola de Computação Avançada - PPGC/UFRGS
https://www.inf.ufrgs.br/ppgc/ecoa-2024-escola-de-computacao-avancada/
17 e 18 de setembro de 2024
Palestra: Advanced Signal Processing for High-Fidelity Image Display
(pt-br: Exibição de Imagens com Alta Fidelidade usando Processamento de Sinais Avançado)
Visual Computing bridges human perception and digital data. It is the reason we can view photos and videos on our devices, create graphics in software like Photoshop, and use augmented reality apps on our smartphones. When conveying information visually, it is crucial to mathematically optimize how the data is presented to enhance clarity and relevance to the viewer. This becomes increasingly significant with the proliferation of display devices of various formats, including smartwatches and virtual reality headsets. In this presentation we will explore how advanced signal-processing techniques can deliver high-fidelity image display, taking into account factors like resolution, viewing conditions, and the human visual system. Advanced topics covered include Generalized Sampling Theory and Space-Frequency Analysis.
Referências
Artigo sobre adaptação de imagens de acordo com condições de visualização (distância, resolução, …):
- Prefilters for Sharp Image Display. Luís Cláudio Gouveia Rocha, Manuel M. Oliveira and Eduardo S. L. Gastal. Computer Graphics Forum. Volume 39 (2020), Number 2, Proceedings of Eurographics 2020. Norrköping, Sweden.
Artigos sobre ajuste de frequências para preservar detalhes em imagens e vídeos:
- Real-Time Frequency Adjustment of Images and Videos. Rafael L. Germano, Manuel M. Oliveira and Eduardo S. L. Gastal Computer Graphics Forum. Volume 40 (2021), Number 2, Proceedings of Eurographics 2021. Vienna, Austria.
- Spectral Remapping for Image Downscaling. Eduardo S. L. Gastal and Manuel M. Oliveira ACM Transactions on Graphics. Volume 36 (2017), Number 4, Proceedings of SIGGRAPH 2017, Article 145. Los Angeles, USA.
Generalized Sampling:
- A fresh look at generalized sampling. Diego Nehab and Hugues Hoppe. Foundations and Trends in Computer Graphics and Vision, v. 8, n. 1, p. 1-84, 2014.
- Sampling - 50 years after Shannon. Michael Unser. Proceedings of the IEEE, v. 88, n. 4, p. 569-587, 2000.
Space-Frequency Analysis:
- Theory of communication. Part 1: The analysis of information. Dennis Gabor. Journal of the Institution of Electrical Engineers-part III: radio and communication engineering, v. 93, n. 26, p. 429-441, 1946.
- Frame analysis of the discrete Gabor-scheme. Meir Zibulski and Yehoshua Y. Zeevi. IEEE transactions on signal processing, v. 42, n. 4, p. 942-945, 1994.
- A wavelet tour of signal processing. Stephane Mallat. Academic Press, 1999.
- Frames and bases: An introductory course. Ole Christensen. Springer Science & Business Media, 2008.
Painel Científico - Perspectiva e Desafios para Pesquisa em Computação
Referências sobre pesquisa e criatividade
- The usefulness of useless knowledge. Abraham Flexner. Harpers, issue 179, 1939. Institute for Advanced Study - Princeton, New Jersey.
- Why Greatness Cannot Be Planned: The Myth of the Objective. Stanley, Kenneth O., and Joel Lehman. Springer, 2015.
Citações
“I sort of feel scientists ought to be doing things that are gonna help society. But actually, that's not how you do your best research. You do your best research when it's driven by curiosity. You just have to understand something. Much more recently I've realized these things [AI and LLMs] could do a lot of harm as well as a lot of good and I've become much more concerned about the effects they're gonna have on society. But that's not what was motivating me. I just wanted to understand: ‘how on earth can the brain learn to do things?’ That's what I want I to know.”
– Geoffrey Hinton, Turing Award Winner
(Source: Geoffrey Hinton | On working with Ilya, choosing problems, and the power of intuition - YouTube)
“We need to think about failure differently. I’m not the first to say that failure, when approached properly, can be an opportunity for growth. But the way most people interpret this assertion is that mistakes are a necessary evil. Mistakes aren’t a necessary evil. They aren’t evil at all. They are an inevitable consequence of doing something new (and, as such, should be seen as valuable; without them, we’d have no originality). And yet, even as I say that embracing failure is an important part of learning, I also acknowledge that acknowledging this truth is not enough. That’s because failure is painful, and our feelings about this pain tend to screw up our understanding of its worth. To disentangle the good and the bad parts of failure, we have to recognize both the reality of the pain and the benefit of the resulting growth.”
– Ed Catmull, Turing Award Winner
(Source Book: Creativity, Inc.: Overcoming the Unseen Forces That Stand in the Way of True Inspiration.)
(via: https://www.themarginalian.org/2014/05/02/creativity-inc-ed-catmull-book/)