A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients

By Javier Portilla, Eero P. Simoncelli. 2000

2,086 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, 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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Generative Visual Manipulation on the Natural Image Manifold (2016, methodology): “A common strategy is to learn local filter or patch models, such as Principal Components, Independent Components, Mixture of Gaussians or wavelet bases [14,15,16].”
A note on the evaluation of generative models (2015, background): “It is therefore unsurprising that other approaches than density estimation are much more effective for image synthesis (Portilla & Simoncelli, 2000; Dosovitskiy et al., 2015; Gatys et al., 2015).”
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks (2015, methodology): “ture synthesis [3, 33, 22], with Portilla & Simoncelli [22] making use of a steerable pyramid wavelet representation [27], similar to our use of a Laplacian pyramid.”
Photographic Image Synthesis with Cascaded Refinement Networks (2017, background): “This distinguishes photorealistic image synthesis from texture synthesis, which can leverage statistical stationarity [34].”
Visualizing Deep Convolutional Neural Networks Using Natural Pre-images (2015, methodology): “Julesz’ ideas were framed probabilistically by Zhu and Mumford [55] and their generation-by-sampling framework was later approximated by Portilla and Simoncelli [35] as a pre-image problem which can be seen as a special case of the inversion method discussed here.”
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis (2016, background): “The work of Gatys et al [7], detailed above, can also be employed in unguided settings [8], outperforming traditional parametric texture synthesis which only uses a linear feature bank and no statistical priors [22].”
LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation (2016, methodology): “Early work in parametric texture synthesis was based on a set of hand-crafted features (Portilla & Simoncelli, 2000).”
Texture Networks: Feed-forward Synthesis of Textures and Stylized Images (2016, methodology): “(Portilla & Simoncelli, 2000) addresses this limitation by proposing to directly find images x that match the desired statistics Φ(x) ≈ Φ(x0), pioneering the pre-image method of (1).”
Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks (2016, methodology): “Early work in parametric texture synthesis developed a set of hand-crafted features that could be used to synthesize textures [Portilla and Simoncelli, 2000].”
Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs (2013, neutral): “We then run the kernel associated with this variable, and accept or reject via the Metropolis-Hastings equation: αMH((S,X)→ (S′, X ′)) = min ( 1, P (ID|f(S′, X ′), X ′)P (S′)P (X ′)q((S′, X ′)→ (S,X)) P (ID|f(S,X), X)P (S)P (X)q((S,X)→ (S′, X ′)) ) We implement our probabilistic graphics programs…”
Exploring the structure of a real-time, arbitrary neural artistic stylization network (2017, background): “Images with identical lower-order spatial statistics appear perceptually identical and capture a visual texture [6, 8, 21, 26].”
Context-based vision system for place and object recognition (2003, background): “The textured images are generated by coercing noise to have the same features as the original image, while matching the statistics of natural images [8].”
Super-Resolution with Deep Convolutional Sufficient Statistics (2015, methodology): “(6) Similarly as other works (Portilla & Simoncelli (2000); H ´ enaff et al. (2014)), we solve (6) using gradient descent, by initializing r (cid:48) = ¯ U ( x ) , where ¯ U is a Point Estimate (which can be linear or non-linear).”
HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models (2019, methodology): “We generate masks using an existing texture-synthesis algorithm [44].”