Self-Supervised Scene De-occlusion
We investigate the problem of scene de-occlusion, which aims to recover the underlying occlusion ordering and complete the invisible parts of occluded ...
GANSpace: Discovering Interpretable GAN Controls
This paper describes a simple technique to analyze Generative Adversarial Networks (GANs) and create interpretable controls for image synthesis.
STEFANN: Scene Text Editor using Font Adaptive Neural Network
The ability to edit text directly on images has several advantages including error correction, text restoration and image reusability.
Cycle Text-To-Image GAN with BERT
Image generation from their respective captions, building on state-of-the-art GAN architectures.
Adversarial Latent Autoencoders
Introducing the Adversarial Latent Autoencoder (ALAE), a general architecture that can leverage recent improvements on GAN training procedures.
BachGAN: High-Res Image Synthesis from Salient Object Layout
We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout.
S2IGAN: Speech-to-Image Generation via Adversarial Learning
A speech-to-image generation (S2IG) framework is proposed which translates speech descriptions to photo-realistic images without using any text ...
In-Domain GAN Inversion for Real Image Editing
We propose an in-domain GAN inversion method, which faithfully reconstructs the input image but also ensures the inverted code to be semantically ...
Differential Subspace Search in High-Dimensional Latent Space
Differential subspace search to allow efficient iterative user exploration in such a space, without relying on domain- or data-specific assumptions.
3D Photography using Context-aware Layered Depth Inpainting
A multi-layer representation for novel view synthesis that contains hallucinated color and depth structures in regions occluded in the original view.
1 - 10
Share a project
Share something interesting you found that's made with ML.
Share what you've made with ML.