116 citations · 284 across the 38 of their papers we have counts for
9 papers · 1 filter
SceneComposer: Any-Level Semantic Image Synthesis
Yu Zeng, Zhe Lin, Jianming Zhang +4
We propose a new framework for conditional image synthesis from semantic layouts of any precision levels, ranging from pure text to a 2D semantic canvas with precise shapes. More s…
Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork
Xin Yuan, Zhe Lin, Jason Kuen +2
We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives. U…
HyperNST: Hyper-Networks for Neural Style Transfer
Dan Ruta, Andrew Gilbert, Saeid Motiian +3
We present HyperNST; a neural style transfer (NST) technique for the artistic stylization of images, based on Hyper-networks and the StyleGAN2 architecture. Our contribution is a n…
RepMix: Representation Mixing for Robust Attribution of Synthesized Images
Tu Bui, Ning Yu, John Collomosse
Rapid advances in Generative Adversarial Networks (GANs) raise new challenges for image attribution; detecting whether an image is synthetic and, if so, determining which GAN archi…
Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis
Trisha Mittal, Ritwik Sinha, Viswanathan Swaminathan +2
As tools for content editing mature, and artificial intelligence (AI) based algorithms for synthesizing media grow, the presence of manipulated content across online media is incre…
SImProv: Scalable Image Provenance Framework for Robust Content Attribution
Alexander Black, Tu Bui, Simon Jenni +3
We present SImProv - a scalable image provenance framework to match a query image back to a trusted database of originals and identify possible manipulations on the query. SImProv…