E
Eero P. Simoncelli
Researcher at Center for Neural Science
Publications - 273
Citations - 83270
Eero P. Simoncelli is an academic researcher from Center for Neural Science. The author has contributed to research in topics: Wavelet & Image processing. The author has an hindex of 81, co-authored 260 publications receiving 68623 citations. Previous affiliations of Eero P. Simoncelli include New York University & Stanford University.
Papers
More filters
Proceedings ArticleDOI
Spherical Retinal Flow for a Fixating Observer
TL;DR: The main contribution of this paper is to formalize the retinal flow for a fixating observer, and to explore the role of the periphery in predicting collision.
Proceedings ArticleDOI
Learning sparse filter bank transforms with convolutional ICA
TL;DR: This work reformulates the ICA problem for transformations computed through convolution with a bank of filters, and develops a generalization of the fastICA algorithm for optimizing the filters over a set of example signals that results in a substantial reduction of computational complexity and memory requirements.
Learning least squares estimators without assumed priors or supervision
Martin Raphan,Eero P. Simoncelli +1 more
TL;DR: In this article, a prior-free estimator is proposed to obtain a least-squares estimator given a measurement process with known statistics, and a set of corrupted measurements of random values drawn from an unknown prior.
Journal ArticleDOI
Maximum differentiation competition: A methodology for comparing quantitative models of perceptual discriminability
Zhou Wang,Eero P. Simoncelli +1 more
Posted ContentDOI
Maximum a posteriori natural scene reconstruction from retinal ganglion cells with deep denoiser priors
TL;DR: This work develops a novel method for approximate maximum a posteriori (MAP) reconstruction by combining a generalized linear model of light responses in retinal neurons and their dependence on spike history and spikes of neighboring cells, with an image prior implicitly embedded in a deep convolutional neural network trained for image denoising.