Using the regularities discovered with the SINBAD approach, we were able to predict more accurately the interpolated pixels from the ones in the original image and were able to generate visually plausible fine spatial details in the expanded image.
📌 3 Key Takeaways
🎯
Objective & Hypothesis:Super-resolution is the creation of higher resolution views of pixel-based images through interpolation between the original pixels.
📊
Key Findings & Data:In this paper, to learn regularities, we make use of the recently proposed SINBAD model of how the cerebral cortical network learns regularities by discovering regularity-simplifying environmental features [5, 14].
💡
Conclusion & Impact:Using the regularities discovered with the SINBAD approach, we were able to predict more accurately the interpolated pixels from the ones in the original image and were able to generate visually plausible fine spatial details in the expanded image.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters
Abstract
Super-resolution is the creation of higher resolution views of pixel-based images through interpolation between the original pixels. Greater super-resolution can be achieved by taking advantage of local regularities inherent in natural images. In this paper, to learn regularities, we make use of the recently proposed SINBAD model of how the cerebral cortical network learns regularities by discovering regularity-simplifying environmental features [5, 14]. Using the regularities discovered with the SINBAD approach, we were able to predict more accurately the interpolated pixels from the ones in the original image and were able to generate visually plausible fine spatial details in the expanded image.
🔖
Cite This Article
KURŞUN, O., FAVOROV, O. (2022). Single-frame super-resolution by inference from learned features. Istanbul University Journal of Electrical and Electronics Engineering, Cilt: 3 - Sayı: 1, 673–681. https://ajindex.com/articles/543900
Attick JJ, Redlich AN., “What does the retina know about natural scenes”. Neural Computation 4: 196-210, 1992
Baker S, Kanade T., “Super-resolution: reconstruction or recognition?” IEEE-EURASIP Workshop on Nonlinear Signal and Image Processing, IEEE, Baltimore, Maryland, 2001 [3] Becker S, Hinton GE “A self-organizing neural network that discovers surfaces in random-dot stereograms.” Nature 355: 161-163, 1992
Clark A, Thornton C., Trading places: computation, representation, and the limits of uninformed learning. Behavioral and Brain Sciences 20: 57-90, 1997
Favorov OV, Ryder D., “SINBAD: A neocortical mechanism for discovering environmental variables and regularities hidden in sensory input.” Biological Cybernetics (submitted), 2002
Field DJ “What is the goal of sensory coding.” Neural Computation 6:559–601,1994
Foldiak P., “Forming sparse representations by local anti-Hebbian learning.” Biological Cybernetics 64: 165-170, 1990
Freeman WT, Jones TR, Pasztor EC., “Example-Based Super-Resolution.” Mitsubishi Electronic Research Laboratory, TR-2001-30, 2001
Keys R., “Bicubic interpolation.” IEEE Trans. Acoust. Speech, Signal Processing 29:1153–1160, 1981 [10] Mumford D., “On the computational architecture of the neocortex. Biological Cybernetics” 65: 135-145, 1991 [11] Olshausen BA, Field DJ.,“Emergence of simple-cell receptive field properties by learning a sparse code for natural images.” Nature 381: 607-609, 1996 [12] Phillips WA, Singer W., “In search of common foundations for cortical computation.” Behavioral and Brain Sciences 20: 657-722, 1997 [13] Rumelhart DE, Hinton GE, Williams RJ., “Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL, PDP Research Group (eds) Parallel distributed processing: explorations in the microstructure of cognition”,MIT Press, Cambridge, Mass, 1: 318-362, 1986 [14] Ryder D, Favorov OV., “The new associationism: a neural explanation for the predictive powers of cerebral cortex.” Brain and Mind 2: 161-194, 2001