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

ICCV 2019 Alaaeldin El-NoubyShikhar SharmaHannes SchulzDevon HjelmLayla El AsriSamira Ebrahimi KahouYoshua BengioGraham W. Taylor

Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Text-to-Image Generation GeNeVA (CoDraw) GeNeVA-GAN F1-score 58.83 # 1
rsim 35.41 # 1
Text-to-Image Generation GeNeVA (i-CLEVR) GeNeVA-GAN F1-score 88.39 # 1
rsim 74.02 # 1