Photo clip art

By Jean-François Lalonde, Derek Hoiem, Alexei A. Efros, Carsten Rother, John M. Winn, Antonio Criminisi. 2007

322 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Semantic Image Synthesis With Spatially-Adaptive Normalization (2019, methodology): “ting photorealistic images conditioning on certain input data. Seminal work computes the output image by stitching pieces from a single image (e.g., Image Analogies [16]) or using an image collection [7,14,23,30,35]. Recent methods directly learn the mapping using neural networks [3,6,22,47,48,54,55”
SUN database: Large-scale scene recognition from abbey to zoo (2010, methodology): “Geometry Specific Histograms: Inspired by “Illumination Context” [16], we build color and texton histograms for each geometric class (ground, vertical, porous, and sky).”
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].”
SUN Database: Exploring a Large Collection of Scene Categories (2014, methodology): “Geo Texton & Geo Color: Inspired by “Illumination Context” [24], we build color and texton histograms for each geometric class (ground, vertical, porous, and sky).”
Learning to Generate Images of Outdoor Scenes from Attributes and Semantic Layouts (2016, background): “In [14], a framework is presented for insertin new objects such as pedestrians into existing photographs of street scenes.”
Scribbler: Controlling Deep Image Synthesis with Sketch and Color (2016, neutral): “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].”
An empirical study of context in object detection (2009, background): “Illumination context [20, 21] captures various parameters of scene illumination, such as sun direction, cloud cover, shadow contrast, whereas weather context would describe meteorological conditions such as current/recent precipitation, wind speed/direction, temperature, as well as the season.”
Building a database of 3D scenes from user annotations (2009, methodology): “To estimate the camera parameters, we follow the procedure outlined in [17], which uses information about the contact location and polygon height ui,j = (vi,j , hi,j) in the image.”
CG2Real: Improving the Realism of Computer Generated Images Using a Large Collection of Photographs (2011, background): “Unfortunately, these approaches require correspondence between the source and target images (or patches), a fairly strong assumption that cannot always be satisfied.”
Recovering Occlusion Boundaries from a Single Image (2007, methodology): “We estimate the ground-vertical contact points using a decision tree classiﬁer based on the shape of the perimeter of a region, as described by Lalonde et al. [15].”
Deep photo: model-based photograph enhancement and viewing (2008, background): “Recent research has shown that various challenging tasks, such as image completion and insertion of objects into photographs [Hays and Efros 2007; Lalonde et al. 2007] can greatly benefit from the availability of the enormous amounts of photographs that had already been captured.”
DenseCut: Densely Connected CRFs for Realtime GrabCut (2015, background): “…has been extremely popular in the last decade and inﬂuenced various computer vision and computer graphics applications, including image editing [LHE ∗ 07,CZM ∗ 10], object detection [SBC05], image classiﬁcation [WCM05], photo composition [CCT ∗ 09, CTM ∗ 13], scene understanding [KT ∗ 09],…”
Quality Assessment for Crowdsourced Object Annotations (2011, methodology): “For instance, applications such as Photo Clip Art [14] or silhouette-based detectors [12] require very accurate annotations.”
Modeling the World from Internet Photo Collections (2008, background): “2005), scene completion (Hays and Efros 2007), and object insertion (Lalonde et al. 2007).”
Amodal Completion and Size Constancy in Natural Scenes (2015, background): “These works, while sharing similar goals to ours, were limited in their scope as they assumed fully visible instances - object recognition technology at the time being a limiting factor.”
A Tree-Based Context Model for Object Recognition (2012, methodology): “data using the algorithm in [17], but instead, we manually encode real-object sizes (e.”