Efros and Freeman Image Quilting Algorithm for Texture Synthesis

Raad, Lara; Galerne, Bruno

doi:10.5201/ipol.2017.171

Cited by 16 publications

(6 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More severe failure cases are shown in the supplementary material (see also the original papers on Gaussian textures [GGM11b, GGM11a]). Regarding the quality of the output textures, let us mention that texton noise outputs do not contain verbatim copy areas contrary to most tiling procedures (see the supplementary material for a comparison with the patch‐based image quilting algorithm [EF01] using the implementation of [RG16]).…”

Section: Resultsmentioning

confidence: 99%

Texton Noise

Galerne

Leclaire

Moisan

2017

Computer Graphics Forum

View full text Add to dashboard Cite

International audienceDesigning realistic noise patterns from scratch is hard. To solve this problem, recent contributions have proposed involved spectral analysis algorithms that enable procedural noise models to faithfully reproduce some class of textures. The aim of this paper is to propose the simplest and most efficient noise model that allows for the reproduction of any Gaussian texture. Texton noise is a simple sparse convolution noise that sums randomly scattered copies of a small bilinear texture called texton. We introduce an automatic algorithm to compute the texton associated with an input texture image that concentrates the input frequency content into the desired texton support. One of the main features of texton noise is that its evaluation only consists to sum thirty texture fetches on average. Consequently texton noise generates Gaussian textures with an unprecedented evaluation speed for noise by example. A second main feature of texton noise is that it allows for high quality on-the-fly anisotropic filtering by simply invoking existing GPU hardware solutions for texture fetches. In addition, we demonstrate that texton noise can be applied on any surface using parameterization-free surface noise and that it allows for noise mixing

show abstract

Section: Resultsmentioning

confidence: 99%

Texton Noise

Galerne

Leclaire

Moisan

2017

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…32 images with a combination of low, average and high target detectabilities were run in a pilot experiment with two participants to select the final set of backgrounds. Randomized backgrounds were created by expanding the original texture image using texture quilting 40 and then cropping a random 666×666 pixel patch. Backgrounds subtended 15×15 degrees visual angle on a gray background with a luminance equal to the mean luminance of the stimuli.…”

Section: /10mentioning

confidence: 99%

A Bayesian model of visual search in natural images and the role of memory

Rashidi

Turpin

Kulik

et al. 2023

Preprint

View full text Add to dashboard Cite

Modelling human eye movements during visual search has been a research topic of interest for many years. Here, we investigate if a Bayesian ideal observer model can be configured to effectively explain human eye movements when searching for a known object target in natural images. We collected eye movements from participants who searched for a known target in 18 different natural textured images and compared their performance and strategy to the ideal observer model. Our model chooses search fixations that maximize information gain, given a probabilistic model of target detectability, at various eccentricities which is in turn approximated from features of a convolutional neural network. We collect and use ground truth data from a second experiment with human observers (observers detecting a target at various eccentricities on the 18 natural textured backgrounds) to fine-tune the parameters of our proposed pipeline for detectability estimation and verify our results. We further study the role of short-term memory in the ideal observer model and find that a model with limited memory best fits the human search patterns. Our results suggest that the visual system's strategy for choosing next fixation location in a visual search task is consistent with a Bayesian ideal observer model.

show abstract

“…To ensure the universality of the algorithm, the similarity of B ′ to A ′ is defined by

λ = ()(, 1 - \frac{(||, info false(A^{'} false) - info false(B^{'} false))}{info false(A^{'} false)}) \times 100 % .

Let λ 0 be the minimal similarity value, thus according to (5), the similarity of a new image block to the synthesised region should conform to λ > λ 0 , and the range of the required feature information on the corresponding edge is as follows:

λ_{0} info false(A^{'} false) \leq info false(B^{'} false) \leq false(2 - λ false) info false(A^{'} false) .

When the image is synthesised, firstly the size of the target image is determined, and then the first image block is randomly selected in the database and placed in the upper left corner. Afterwards, the image blocks are placed in the scanning order [36] with required feature information that is searched in the database according to (6). Finally, the selected image blocks are copied to the designated area and stitched to the synthesised area by Dijkstra algorithm.…”

Section: Generation Of Label Imagementioning

confidence: 99%