the archive

#image synthesis

4 results

cs.CV2019

Image Synthesis with a Single (Robust) Classifier

Shibani Santurkar, Dimitris Tsipras, Brandon Tran +3

The paper demonstrates that a single off‑the‑shelf classifier, when trained to be adversarially robust, can be used for various image synthesis tasks by directly manipulating salie…

#image synthesis#adversarial robustness#robust classifiers#feature manipulation

cs.CV2019

Editing Text in the Wild

Liang Wu, Chengquan Zhang, Jiaming Liu +4

The paper introduces SRNet, an end‑to‑end network that can replace or modify words in natural images while preserving the original text style and background, using separate modules…

#text editing#image synthesis#style transfer#background inpainting

cs.CV2019

One-shot Face Reenactment

Yunxuan Zhang, Siwei Zhang, Yue He +3

The paper introduces a one-shot face reenactment framework that can transfer pose and expression using only a single target image by disentangling appearance and shape in latent sp…

#face reenactment#one-shot learning#image synthesis#latent representation

cs.LG2019

Generative Adversarial Networks (GANs): What it can generate and What it cannot?

P Manisha, Sujit Gujar

The paper surveys theoretical work on GANs, organizing existing research by the training problems they address and summarizing how each approach tackles issues like mode collapse a…

#generative adversarial networks#theoretical analysis#training stability#mode collapse