The steerable pyramid: a flexible architecture for multi-scale derivative computation

By E. Simoncelli, W. T. Freeman. 1995

How researchers see this paper

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

Citations in the corpus

Group Invariant Scattering (2011, background): “The parameter γ then specifies an angle [19].”
Context-based vision system for place and object recognition (2003, methodology): “We use a steerable pyramid [11] with 6 orientations and 4 scales applied to the intensity (monochrome) image.”
Texture synthesis and the controlled generation of natural stimuli using convolutional neural networks (2015, methodology): “The model took its inspiration from the early visual system and is based on a set of carefully handcrafted summary statistics computed on the responses of a linear ﬁlter bank called Steerable Pyramid [18].”
Recovering intrinsic images from a single image (2005, methodology): “The classifier was trained to label the coefficients of a steerable pyramid [20] as caused by either shading or a reflectance change.”
The design of approximate Hilbert transform pairs of wavelet bases (2002, methodology): “Freeman and Adelson employ the Hilbert transform in the development of steerable filters [5], [20].”
Video Acceleration Magnification (2017, background): “With the apprise of the complex-steerable pyramid [9,20,23], the use of phasebased motion has been considered not only in the context of motion magnification but also for other motion-related applications.”
The dual-tree complex wavelet transform (2005, background): “The closest alternative to the dual-tree CWT is probably the complex (approximately) analytic form of the steerable pyramid[95, 96].”
Top-down control of visual attention in object detection (2003, methodology): “Here, we decompose each color subband using a steerable pyramide [7] with 4 scales and 4 orientations (fig.”
Statistical Learning with Sparsity: The Lasso and Generalizations (2015, background): “2 is known as the steerable pyramid (Simoncelli and Freeman 1995).”
Design of steerable filters for feature detection using canny-like criteria (2004, methodology): “In this paper, we propose to reconcile the two methodo-logies—computational approach and steerable filterbanks—-by presenting a general strategy for the design of 2D steerable feature detectors.”
RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment (2012, methodology): “We present the details of the algorithms in the following section, reserving the perceptual interpretation of the algorithms for a later section.”
Phase-based video motion processing (2013, result): “Figure 8: Comparison of our result on the camera sequence (d) with the result of Wu et al. [2012] (a), denoised by two state-ofthe-art video denoising algorithms: VBM3D [Dabov et al.”
Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. (2006, methodology): “The Luminance channel (computed as the average of the R, G, B channels) is decomposed using a steerable pyramid (Simoncelli & Freeman, 1995) with 6 orientations and 4 spatial frequency scales.”
Image information and visual quality (2006, methodology): “In this paper, we model each subband of a scale-space-orientation wavelet decomposition (such as the steerable pyramid [33]) of an image as a GSM RF.”
A Mathematical Motivation for Complex-Valued Convolutional Networks (2015, unknown): “Further information is available in the original work of Daubechies (1992), Meyer (1993), Coifman et al. (1994), Coifman and Donoho (1995), Simoncelli and Freeman (1995), Meyer and Coifman (1997), LeCun et al. (1998), Donoho et al. (2003), Srivastava et al. (2003), Rabiner and Schafer (2007), and…”
Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “Following [26], we first extract the lowlevel features, including RGB color, steerable pyramids [79] and Gabor filter [80], to construct a 53-dimension feature representation.”
The SURE-LET Approach to Image Denoising (2007, methodology): “Higher directional sensitivity can be achieved by the so-called shiftable or steerable multiscale transforms [46, 47].”