Two-scale tone management for photographic look

By Soonmin Bae, Sylvain Paris, Frédo Durand. ACM Transactions on Graphics, 2006

389 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/33a23e37be8402b51a1d74b2254b2723741223dd

How researchers see this paper

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

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

Citations in the corpus

Image smoothing via L0 gradient minimization (2011, methodology): “It is a less serious problem, because either gradient-domain operation followed by image reconstruction [Bae et al. 2006] or by directly modifying color [Durand and Dorsey 2002; Kass and Solomon 2010] can be employed.”
Guided Image Filtering (2010, background): “Though this filter is effective in many situations, it may have unwanted gradient reversal artifacts [15], [16], [8] near edges (discussed in Section 3.4).”
Display adaptive tone mapping (2008, methodology): “2006], stylized rendering [Bae et al. 2006] and finding other means than luminance to extend image contrast [Smith et al.”
A Closed-form Solution to Photorealistic Image Stylization (2018, background): “, color transfer [25, 24, 31] or tone transfer [1]) or are limited to specific scenarios (e.”
Deep Photo Style Transfer (2017, methodology): “In that respect, our algorithm is related to the techniques that operate in the photo realm [1, 4, 8, 14, 15, 17].”
A Fast Approximation of the Bilateral Filter Using a Signal Processing Approach (2006, methodology): “2001), dynamic range compression (Durand and Dorsey 2002), illumination correction (Elad 2005), and photograph enhancement (Eisemann and Durand 2004; Petschnigg et al. 2004; Bae et al. 2006).”
Recognizing Materials Using Perceptually Inspired Features (2013, methodology): “We perform bilateral filtering (Bae et al. 2006) on the original images to obtain (b) the base images.”
Edge-preserving decompositions for multi-scale tone and detail manipulation (2008, methodology): “Durand and Dorsey [2002] describe a variant designed specifically to avoid halos along thin, high contrast features, while Bae et al. [2006] detect and fix reversed gradients when manipulating the detail layer.”
Exploring features in a Bayesian framework for material recognition (2010, methodology): “In order to extract information about surface structure, we followed the idea in [1], of smoothing an image by bi-lateral ﬁ ltering [12] and then using the residual image for further analysis.”
Learning photographic global tonal adjustment with a database of input/output image pairs (2011, methodology): “Bae et al. [3] and Hertzmann et al. [9] adjust photos using a model provided by the user.”
Fast Image Processing with Fully-Convolutional Networks (2017, background): “Techniques developed in the last decade can dramatically enhance detail [24, 69, 26, 28, 60], transform the image by applying a master photographer’s style [7, 5], smooth the image for the purpose of abstraction [73, 76, 79], and eliminate the effects of atmospheric scattering [25, 35, 27, 9].”
Fast End-to-End Trainable Guided Filter (2018, background): “For example, image processing techniques enable smooth an image while preserving the edges [39, 41, 43], enhance the details of an image [13, 36], transfer style from a reference image [3, 4],”
CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs (2011, background): “Color and tone transfers are completely automatic, and texture transfer can be controlled by adjusting a few parameters.”
Local Laplacian filters: edge-aware image processing with a Laplacian pyramid (2011, methodology): “While some of these shortcomings can be alleviated in post-processing, e.g., bilateral ﬁltered edges can be smoothed [Durand and Dorsey 2002; Bae et al. 2006; Kass and Solomon 2010], this induces additional computation and parameter setting, and a method producing good results directly is…”