Sketch2Photo: internet image montage

By Tao Chen, Ming-Ming Cheng, Ping Tan, Ariel Shamir, Shimin Hu. 2009

707 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Semantic Image Synthesis With Spatially-Adaptive Normalization (2019, background): “Compared to earlier non-parametric methods [7, 16, 23], learning-based methods typically run faster during test time and produce more realistic results.”
Image-to-Image Translation with Conditional Adversarial Networks (2016, background): “, [14, 23, 18, 8, 10, 50, 30, 36, 16, 55, 58]), despite the fact that the setting is always the same: predict pixels from pixels.”
Generative Visual Manipulation on the Natural Image Manifold (2016, background): “xel marked with this brush we constrain the color f g(I) = I p= v g of a pixel pto the selected values v g. Sketching brush: The sketching brush allows the user to outline the shape or add ne details [36]. We constrain f g(I) = HOG(I) p a dierentiable HOG descriptor [37] at a certain location pin th”
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, methodology): “Our interface is inspired by prior data-driven graphics systems [6, 23, 28].”
Scribbler: Controlling Deep Image Synthesis with Sketch and Color (2016, background): “Previously, the most successful methods tended to be non-parametric approaches which found clever ways to reuse existing image fragments [30, 9, 15, 22, 6, 3].”
Cali-Sketch: Stroke Calibration and Completion for High-Quality Face Image Generation from Poorly-Drawn Sketches (2019, methodology): “Given a sketch plus overlaid text labels as input, Sketch2Photo [18] and Photo-Sketcher [19] automatically synthesize realistic pictures by seamlessly composing objects and backgrounds based on sketch searching and image compositing.”
EGNet: Edge Guidance Network for Salient Object Detection (2019, background): “It has received widespread attention recently and been widely used in many vision and image processing related areas, such as contentaware image editing [6], object recognition [42], photosynth [4], non-photo-realist rendering [41], weakly supervised semantic segmentation [19] and image retrieval [1”
How do humans sketch objects? (2012, background): “Synthesis systems that are based on user sketches alone have to rely on huge amounts of data to off-set the problem of geometric dissimilarity between sketches and image content [Eitz et al. 2011b] or require users to augment the sketches with text labels [Chen et al. 2009].”
Deep Sketch-Guided Cartoon Video Inbetweening (2021, background): “[12] compose a realistic picture from a freehand sketch annotated with text labels, which is realized by stitching several text-related photographs discovered online.”
Salient Object Detection via Structured Matrix Decomposition (2017, methodology): “Salient Object Detection via Structured Matrix Decomposition Houwen Peng, Bing Li, Haibin Ling, Weiming Hu, Weihua Xiong, and Stephen J. Maybank Abstract—Low-rank recovery models have shown potential for salient object detection, where a matrix is decomposed into a low-rank matrix representing image”
3-D Object Retrieval and Recognition With Hypergraph Analysis (2012, background): “Visual analyses [17]–[22] have shown its superiority in multimedia applications.”
TextureGAN: Controlling Deep Image Synthesis with Texture Patches (2017, background): “They are typically data-driven or example-based, i.e., directly exploit and borrow existing image pixels for the target tasks [1, 2, 6, 13, 27].”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, background): “It has a wide range of applications, including video/image segmentation [17, 40], object recognition [46], visual tracking [3], foreground maps evaluation [14, 15], image retrieval [6,16,22,38], content-aware image editing [8], information discovery [58], photo synthesis [5, 29], and weakly supervis”
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation (2015, methodology): “We measure the impreciseness and incompleteness of the SaliencyCut [20] segmentation as in [40].”
Salient object detection: A survey (2014, methodology): “theses are generated as a set of ﬁgure-ground seg15 (a) Content aware resizing [59] (b) Image collage [191] (c) View selection [192] (d) Unsupervised learning [193] (e) Mosaic [194] (f) Image montage [195] (g) Object manipulation [196] (h) Semantic colorization [197] Fig. 9. Sample applications of s”
Data-driven visual similarity for cross-domain image matching (2011, background): “…scene and video completion [Wexler et al. ; Hays and Efros 2007; Whyte et al. 2009], photo restoration [Dale et al. 2009], assembling photo-realistic virtual spaces [Kaneva et al. 2010; Chen et al. 2009], and even making CG imagery more realistic [Johnson et al. 2010], to give but a few examples.”
Sketch-based manga retrieval using manga109 dataset (2015, background): “Sketch-based interaction is the most natural way for humans to describe visual objects, and is widely adapted not only for image retrieval, but also in many applications such as shape modeling [36], image montage [37], texture design [38], and as a querying tool for recognizing objects [5], [39].”
CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs (2011, background): “Rosales et al. [9] relaxed this assumption by framing the problem as a large inference problem, where both the position and appearance of the patches are inferred from a pair of images without correspondence.”