PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
Text to image generation and editing: A survey
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.
citing papers explorer
-
PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation
PortraitGen integrates real-image exemplars into GRPO sampling and applies dual rewards (OmniReward and AI-Portrait) to improve photorealism, claiming better results than baselines on a new PortraitBench.
-
EmoCtrl: Controllable Emotional Image Content Generation
EmoCtrl generates images faithful to content prompts while expressing target emotions via textual/visual enhancement modules and emotion-driven preference optimization.