Interactive Digital Photomontage

By Aseem Agarwala, Mira Dontcheva, Maneesh Agrawala, Steven Mark Drucker, Alex Colburn, Brian Curless, David Salesin, Michael F. Cohen. ACM Transactions on Graphics, 2004

1,001 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8999529133992a31acee7aa09b01697aa65c9f92

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

Citations in the corpus

Parallax-Tolerant Image Stitching (2014, methodology): “While advanced image composition techniques, such as seam cutting [2, 12] and blending [4, 17], can relieve these artifacts, they cannot address significant misalignment.”
Fourier Analysis of the 2D Screened Poisson Equation for Gradient Domain Problems (2008, background): “Examples include tone-mapping of high dynamic range images [10], Poisson image editing [11], and digital photomontage [12].”
DeepPermNet: Visual Permutation Learning (2017, neutral): “[2] 52.”
Synthesizing structured image hybrids (2010, background): “These allow a user to combine content from multiple source images [Agarwala et al. 2004] or to rearrange content within a given image [Cho et al. 2008; Pritch et al. 2009], possibly at interactive rates [Barnes et al. 2009].”
Efficient Belief Propagation with Learned Higher-Order Markov Random Fields (2006, background): “In general finding exact solutions to these estimation problems is hard for loopy graphs, but approximation approaches based on graph cuts [1, 3, 17, 18] and loopy belief propagation [6, 18, 19] have been found to often work well in practice.”
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis (2016, background): “These can be either explicitly provided by the user [1, 2, 5, 7, 12, 16, 27], or learned from non-local image statistics [11, 18, 30].”
Two-scale tone management for photographic look (2006, methodology): “2002] and montages [Pérez et al. 2003; Agarwala et al. 2004].”
A Comparative Study of Energy Minimization Methods for Markov Random Fields (2006, background): “On the Photomontage benchmark, expansion moves perform best, which provides some justification for the fact that this algorithm is used by various image stitching applications [12, 26].”
Removing photography artifacts using gradient projection and flash-exposure sampling (2005, methodology): “Our gradient domain techniques are related to those used for HDR compression [Fattal et al. 2002], image editing [Perez et al. 2003], image fusion for context enhancement [Raskar et al. 2004b], creating photomontages [Agarwala et al. 2004] and image matting [Sun et al. 2004].”