Realrag: Retrieval-augmented Realistic Image Generation Via Self-reflective Contrastive Learning

Abstract

Recent text-to-image generative models, e.g., Stable Diffusion V3 and Flux, have achieved notable progress. However, these models are strongly restricted to their limited knowledge, a.k.a., their own fixed parameters, that are trained with closed datasets. This leads to significant hallucinations or distortions when facing fine-grained and unseen novel real-world objects, e.g., the appearance of the Tesla Cybertruck. To this end, we present the first real-object-based retrieval-augmented generation framework (RealRAG), which augments fine-grained and unseen novel object generation by learning and retrieving real-world images to overcome the knowledge gaps of generative models. Specifically, to integrate missing memory for unseen novel object generation, we train a reflective retriever by self-reflective contrastive learning, which injects the generator's knowledge into the sef-reflective negatives, ensuring that the retrieved augmented images compensate for the model's missing knowledg

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylyu2025realrag

Related papers

• Imagerag: Dynamic Image Retrieval For Reference-guided Image Generation (2025)0.00
• AR-RAG: Autoregressive Retrieval Augmentation For Image Generation (2025)0.00
• Cross-modal RAG: Sub-dimensional Text-to-image Retrieval-augmented Generation (2025)0.00
• Murag: Multimodal Retrieval-augmented Generator For Open Question Answering Over Images And Text (2022)14.66
• RAVID: Retrieval-augmented Visual Detection: A Knowledge-driven Approach For Ai-generated Image Identification (2025)0.00
• Text-guided Synthesis Of Artistic Images With Retrieval-augmented Diffusion Models (2022)8.29
• Visual-rag: Benchmarking Text-to-image Retrieval Augmented Generation For Visual Knowledge Intensive Queries (2025)0.00
• Neurosymbolic Retrievers For Retrieval-augmented Generation (2026)0.00