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.
generative-adversarial-networks salient-object-layout image-generation image-synthesis pytorch computer-vision research
Resource links
Details
Objectives & Highlights

Two main challenges spring from this new task: • (i) how to generate fine-grained details and realistic textures without segmentation map input; and • (ii) how to create a background and weave it seamlessly into standalone objects. To tackle this, we propose Background Hallucination Generative Adversarial Network (BachGAN), which first selects a set of segmentation maps from a large candidate pool via a background retrieval module, then encodes these candidate layouts via a background fusion module to hallucinate a suitable background for the given objects.

Don't forget to tag @Cold-Winter in your comment.

Authors
Ph.D. Student in CRCV of UCF.
Share this project
Similar projects
GAN Lab
An Interactive, Visual Experimentation Tool for Generative Adversarial Networks
Deep Generative Models
CS236: A comprehensive course to learn about generative modeling techniques in deep learning.
PyTorch Tutorial for Deep Learning Researchers
This repository provides tutorial code for deep learning researchers to learn PyTorch.
Adversarial Latent Autoencoders
Introducing the Adversarial Latent Autoencoder (ALAE), a general architecture that can leverage recent improvements on GAN training procedures.