Controllable Semantic Image Inpainting
By Jin Xu, Yee Whye Teh. 2018
7 citations recorded by the source corpus.
We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generative model bringing together: an encoder which can encode an arbitrary set of observed pixels, latent variables which are trained to represent disentangled factors of variations, and a bidirectional PixelCNN model. We experimentally demonstrate that our method can generate plausible inpainting results matching the user-specified semantics, but is still coherent with observed pixels. We justify our choices of architecture and training regime through more experiments.
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
- David Kristjanson Duvenaud
- Luc Van Gool
- Xuechen Li
- Jitendra Malik
- Xiaogang Wang
- Ming-Hsuan Yang
- Dacheng Tao
- Roger Baker Grosse
Citations in the corpus
- Isolating Sources of Disentanglement in VAEs (2018, methodology): “The simplicity of our method allows easy integration into different frameworks [43].”