DFO

10 papers with code · Computer Vision
Subtask of Image Generation

Providing Opportunities for young people to observe, participate and influence decisions that impact their future

State-of-the-art leaderboards

Greatest papers with code

StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

19 Oct 2017hanzhanggit/StackGAN

In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images.

DFO

StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks

ICCV 2017 hanzhanggit/StackGAN

Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications.

DFO

Generative Adversarial Text to Image Synthesis

17 May 2016hanzhanggit/StackGAN

Automatic synthesis of realistic images from text would be interesting and useful, but current AI systems are still far from this goal.

ADVERSARIAL TEXT DFO

AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

CVPR 2018 taoxugit/AttnGAN

In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation.

 SOTA for DFO on CUB

DFO TEXT MATCHING

Generating Images from Captions with Attention

9 Nov 2015emansim/text2image

Motivated by the recent progress in generative models, we introduce a model that generates images from natural language descriptions.

DFO

Provably Robust Blackbox Optimization for Reinforcement Learning

7 Mar 2019FlorianWilk/SpotMicroAI

Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics.

DFO

Generating Multiple Objects at Spatially Distinct Locations

ICLR 2019 tohinz/multiple-objects-gan

Our experiments show that through the use of the object pathway we can control object locations within images and can model complex scenes with multiple objects at various locations.

CONDITIONAL IMAGE GENERATION DFO

MC-GAN: Multi-conditional Generative Adversarial Network for Image Synthesis

3 May 2018HYOJINPARK/MC_GAN

This block enables MC-GAN to generate a realistic object image with the desired background by controlling the amount of the background information from the given base image using the foreground information from the text attributes.

DFO

Tell, Draw, and Repeat: Generating and Modifying Images Based on Continual Linguistic Instruction

24 Nov 2018Maluuba/GeNeVA_datasets

Conditional text-to-image generation is an active area of research, with many possible applications.

DFO

MirrorGAN: Learning Text-to-image Generation by Redescription

CVPR 2019 byby221b/PaperReading

Generating an image from a given text description has two goals: visual realism and semantic consistency.

DFO