Exposure Fusion

By Tom Mertens, Jan Kautz, Frank Van Reeth. Pacific Conference on Computer Graphics and Applications, 2009

828 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f0fd09641b97fb8d406437dba27de6d5db0fa58f

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

In Media Technology

Citations in the corpus

Objective Quality Assessment of Tone-Mapped Images (2013, neutral): “[36].”
Pixel-level image fusion: A survey of the state of the art (2017, methodology): “…35] coeﬃcient [4, 17], window[18], and region[13] based activity level measurement, choose-max[28], optimization based method[36], weighted-average[4, 37, 38], and substitution[12, 15] based coeﬃ-cients combining, window and region based consistency veriﬁcation[5, 39], cross-scale fusion rule…”
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement (2020, methodology): “We follow existing practices [19, 20] to setE as the gray level in the RGB color space.”
Multi-focus image fusion with a deep convolutional neural network (2017, methodology): “These two kinds of weight maps are multiplied to generate the ﬁnal weight map as presented in [67] .”
Single Image Dehazing by Multi-Scale Fusion (2013, methodology): “Different than previous single image dehazing approaches, our technique is built on the principle of image fusion, a wellstudied topic of computational imaging that has found many useful applications such as interactive photomontage [25], image editing [26], image compositing [27], [28] and HDR imag”
Deep reverse tone mapping (2017, methodology): “We can also use the method by Mertens et al. [2007], which does not require exposure durations as input, to generate a tone-mapped LDR image without generating an HDR image.”
Burst photography for high dynamic range and low-light imaging on mobile cameras (2016, methodology): “The tone mapping method we have chosen is a variant of exposure fusion [Mertens et al. 2007].”
High Dynamic Range Imaging (2015, methodology): “This is achieved by blending (fusing) several JPEG images taken at different exposures where each blending weight is determined by a measure of quality, such as local contrast, or color distribution [102].”
Generative Diffusion Prior for Unified Image Restoration and Enhancement (2023, background): “ing the previous works [52, 53], E is set as the gray level in the RGB color space.”
Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity (2020, methodology): “To verify the effectiveness in multi-exposure image fusion, we compare it with three existing methods: DSIFT (Hayat and Imran 2019), EF (Mertens, Kautz, and Van Reeth 2007) and AWPIGG (Lee, Park, and Cho 2018).”
Color Balance and Fusion for Underwater Image Enhancement (2018, methodology): “Originally, in an exposure fusion context [55], the exposedness weight map had been introduced to reduce the weight of pixels that are under- or over-exposed.”
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation (2021, methodology): “We follow existing practices [30], [31] to set E as the gray level in the RGB color”
Robust Multi-Exposure Image Fusion: A Structural Patch Decomposition Approach (2017, methodology): “H. Li and L. Zhang are with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong (e-mail: cshli@comp.polyu.edu.hk; cslzhang@comp.polyu.edu.hk).”
Referenceless Prediction of Perceptual Fog Density and Perceptual Image Defogging (2015, methodology): “, edges) over a wide range of scales, and that the multiscale method provides a convenient way to incorporate local image details over varying resolutions [19], [54].”
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement (2017, background): “Other fusion techniques like multi-scale fusion [42] and Boosting Laplacian Pyramid fusion [43] can also be used to obtain a better fusion results.”