Naive Bayes Super-Resolution Forest

By Jordi Salvador, Eduardo Pérez-Pellitero. 2015

118 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (2016, background): “ighborhood approaches to overﬁt and formulate a more general map of example pairs using kernel ridge regression. The regression problem can also be solved with Gaussian process regression [27], trees [46] or Random Forests [47]. In Dai et al. [6] a multitude of patch-speciﬁc regressors is learned an”
End-to-End Image Super-Resolution via Deep and Shallow Convolutional Networks (2016, methodology): “The compared methods include the traditional bicubic interpolation and nine popular learning based methods: the scale-up using sparse representation (SUSR) proposed by Zeyde et al. [7], adjusted anchored neighborhood regression method (A + ) [11], two forests based methods, i.e. , ARFL [12] and NBSR”
Balanced Two-Stage Residual Networks for Image Super-Resolution (2017, background): “Random forest can be built for SR without dictionary learning in the work of [29, 28].”
Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections (2016, methodology): “For super-resolution, we compare our network with SRCNN [7], NBSRF [25], CSCN [30], CSC [10], TSE [13] and ARFL+ [26] on three datasets: Set5, Set14 and BSD100.”
Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections (2016, methodology): “We compare our network with SRCNN [28], NBSRF [53], CSCN [17], CSC [16], TSE [54] and ARFL+ [55] on three dataset: Set5, Set14 and BSD100.”
PSyCo: Manifold Span Reduction for Super Resolution (2016, background): “Sublinear search structures such as trees, hashing functions or forests [17, 25, 19, 18] have been proposed in order to reduce the regressor search complexity.”