Semantic Photo Synthesis

68 citations recorded by the source corpus.

How researchers see this paper

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

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”
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].”
TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context (2007, background): “Semantic Photo Synthesis In Johnson et al. (2006), the user draws onto a canvas both particular objects (the Taj Mahal, for example) and regions assigned a particular semantic label (sky, water, car, etc).”
Sketch2Photo: internet image montage (2009, methodology): “2007]) while being less restricted during image selection ([Johnson et al. 2006]).”
Image Reconstruction from Bag-of-Visual-Words (2014, background): “cal descriptors without their geometric information. Our work is the ﬁrst to address such a feature. 2.2 Image Generation A conventional approach for image generation is to synthesize multiple images [20], [21] because direct generation of images is rather difﬁcult. They can produce clear and aesthe”