De-emphasis of distracting image regions using texture power maps

Su, Sara L.; Durand, Frédo; Agrawala, Maneesh

doi:10.1145/1080402.1080445

Cited by 44 publications

(32 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, working at multiple scales allows us to better capture the frequency profile of these elements, akin to the work of Heeger and Bergen [1995]. Our technique builds upon the notion of power maps [Malik and Perona 1990;Su et al 2005;Li et al 2005;Bae et al 2006] to estimate the local energy in each image frequency subband. Similarly to Li et al [2005], to prevent aliasing problems, we do not downsample the subbands.…”

Section: Multiscale Transfer Of Local Contrastmentioning

confidence: 99%

Style transfer for headshot portraits

et al. 2014

Self Cite

View full text Add to dashboard Cite

Headshot portraits are a popular subject in photography but to achieve a compelling visual style requires advanced skills that a casual photographer will not have. Further, algorithms that automate or assist the stylization of generic photographs do not perform well on headshots due to the feature-specific, local retouching that a professional photographer typically applies to generate such portraits. We introduce a technique to transfer the style of an example headshot photo onto a new one. This can allow one to easily reproduce the look of renowned artists. At the core of our approach is a new multiscale technique to robustly transfer the local statistics of an example portrait onto a new one. This technique matches properties such as the local contrast and the overall lighting direction while being tolerant to the unavoidable differences between the faces of two different people. Additionally, because artists sometimes produce entire headshot collections in a common style, we show how to automatically find a good example to use as a reference for a given portrait, enabling style transfer without the user having to search for a suitable example for each input. We demonstrate our approach on data taken in a controlled environment as well as on a large set of photos downloaded from the Internet. We show that we can successfully handle styles by a variety of different artists.

show abstract

Section: Multiscale Transfer Of Local Contrastmentioning

confidence: 99%

Style transfer for headshot portraits

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…28 Therefore, in order to describe an image more accurately with fewer noises by considering the dissimilarity between different scales, a rectification process is implemented in our work. Based on the Laplacian stacks, and inspired by power maps proposed in Refs.…”

Section: Energy Mapmentioning

confidence: 99%

“…(13) and (14), from the macropoint of view, for two frames, we can get a final energy flow field sequence abbreviated as fV S ¼ ðν kþ1 Sx ; ν kþ1 Sy Þj0 ≤ S ≤ mg on multiple scales. Because for high-pass scales, the energy map averages response over a larger region of the image; 28 to represent the details produced by tiny variation during the time interval δt and to guarantee the avoidance of noise simultaneously, we reconstruct energy flow field on the velocity layer rather than on the energy map layer for expressing image correspondence relationship using V 0 , which can be computed by iteration as follows: E Q -T A R G E T ; t e m p : i n t r a l i n k -; e 0 1 5 ; 3 2 6 ; 7 5 2…”

Section: Energy Flow Field Reconstructionmentioning

confidence: 99%

Energy flow: image correspondence approximation for motion analysis

Wang

Fang

2016

Opt. Eng

View full text Add to dashboard Cite

Abstract. We propose a correspondence approximation approach between temporally adjacent frames for motion analysis. First, energy map is established to represent image spatial features on multiple scales using Gaussian convolution. On this basis, energy flow at each layer is estimated using Gauss-Seidel iteration according to the energy invariance constraint. More specifically, at the core of energy invariance constraint is "energy conservation law" assuming that the spatial energy distribution of an image does not change significantly with time. Finally, energy flow field at different layers is reconstructed by considering different smoothness degrees. Due to the multiresolution origin and energy-based implementation, our algorithm is able to quickly address correspondence searching issues in spite of background noise or illumination variation. We apply our correspondence approximation method to motion analysis, and experimental results demonstrate its applicability. © The Authors. Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

“…In this paragraph, we describe a simple and computationally efficient texture estimator although one could use other models [23,24]. Formally, our scheme is:…”

Section: Reducing the Curl On The Boundarymentioning

confidence: 99%

Error-Tolerant Image Compositing

2012

View full text Add to dashboard Cite

Abstract. Gradient-domain compositing is an essential tool in computer vision and its applications, e.g., seamless cloning, panorama stitching, shadow removal, scene completion and reshuffling. While easy to implement, these gradient-domain techniques often generate bleeding artifacts where the composited image regions do not match. One option is to modify the region boundary to minimize such mismatches. However, this option may not always be sufficient or applicable, e.g., the user or algorithm may not allow the selection to be altered. We propose a new approach to gradient-domain compositing that is robust to inaccuracies and prevents color bleeding without changing the boundary location. Our approach improves standard gradient-domain compositing in two ways. First, we define the boundary gradients such that the produced gradient field is nearly integrable. Second, we control the integration process to concentrate residuals where they are less conspicuous. We show that our approach can be formulated as a standard least-squares problem that can be solved with a sparse linear system akin to the classical Poisson equation. We demonstrate results on a variety of scenes. The visual quality and run-time complexity compares favorably to other approaches.

show abstract

De-emphasis of distracting image regions using texture power maps

Cited by 44 publications

References 20 publications

Style transfer for headshot portraits

Style transfer for headshot portraits

Energy flow: image correspondence approximation for motion analysis

Error-Tolerant Image Compositing

Contact Info

Product

Resources

About