Multiscale shape and detail enhancement from multi-light image collections

By Raanan Fattal, Maneesh Agrawala, Szymon Rusinkiewicz. ACM Transactions on Graphics, 2007

378 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9c52d7469853d82cc7c5ee8102be2912278e8098

How researchers see this paper

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

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Luc Van Gool
3. Jiaya Jia
4. Dacheng Tao
5. Xiaogang Wang
6. Xiaoou Tang
7. Kaiming He
8. Chen Change Loy

In Media Technology

1. B. K. Shreyamsha Kumar
2. Raanan Fattal
3. Jiaya Jia
4. Li Xu
5. Xiaoou Tang
6. Ming-Hsuan Yang
7. Kaiming He
8. Yi Xu

Citations in the corpus

• Multiresolution Bilateral Filtering for Image Denoising (2008, positive): “Also, [31] utilizes the bilateral filter in a multiresolution scheme for shape and detail enhancement from multiple images .)”
• Image fusion based on pixel significance using cross bilateral filter (2013, methodology): “In Fattal et al. [35], BF has been used for multiscale decomposition of multilight image collections for shape and detail enhancement.”
• Weighted Guided Image Filtering (2016, background): “Typical examples include image de-noising [1], [2], fusion of differently exposed images [3], tone mapping of high dynamic range (HDR) images [4], detail enhancement via multi-lighting images [5], texture transfer from a source image to a destination image [6], single image haze removal [7], and etc”
• Guided Image Filtering (2010, methodology): “It has been widely used in noise reduction [28], HDR compression [15], multiscale detail decomposition [29], and image abstraction [30].”
• Image smoothing via L0 gradient minimization (2011, background): “Contrast expansion or compression enables detail magnification [Bae et al. 2006; Fattal et al. 2007] and HDR compression ACM Transactions on Graphics, Vol. 30, No. 6, Article 174, Publication date: December 2011.”
• A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing (2017, methodology): “We tested 8 image smoothing algorithms for the network to approximate, including bilateral filter (BLF) [26], iterative bilateral filter (IBLF) [8], rolling guidance filter (RGF) [42], RTV texture smoothing ]) Figure 6.”
• Edge-avoiding wavelets and their applications (2009, methodology): “This test shows that our output is halo-free with an increased fine-scale detail and does not show the gradient-reversals seen in the result of [Fattal et al. 2007].”