# RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning

arXiv: https://arxiv.org/abs/2502.00848 · HTML: https://mlsanity.com/paper/2502.00848/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 56 of its 70 references that are in the map.
- First posted on arXiv 2 Feb 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)
- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 56)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Generalization through Memorization: Nearest Neighbor Language Models](https://mlsanity.com/paper/1911.00172/) (2019)
- [REPLUG: Retrieval-Augmented Black-Box Language Models](https://mlsanity.com/paper/2301.12652/) (2023)
- [Show-o: One Single Transformer to Unify Multimodal Understanding and Generation](https://mlsanity.com/paper/2408.12528/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Active Retrieval Augmented Generation](https://mlsanity.com/paper/2305.06983/) (2023)
- [Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model](https://mlsanity.com/paper/2408.11039/) (2024)
- [PointCLIP: Point Cloud Understanding by CLIP](https://mlsanity.com/paper/2112.02413/) (2021)
- [Generative Multimodal Models are In-Context Learners](https://mlsanity.com/paper/2312.13286/) (2023)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)

## Built on by (most cited first, 20 of 20)

- [Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook](https://mlsanity.com/paper/2503.18016/) (2025)
- [Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?](https://mlsanity.com/paper/2505.11907/) (2025)
- [ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation](https://mlsanity.com/paper/2502.09411/) (2025)
- [Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2506.05872/) (2025)
- [SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting](https://mlsanity.com/paper/2506.08710/) (2025)
- [CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation](https://mlsanity.com/paper/2603.08652/) (2026)
- [BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions](https://mlsanity.com/paper/2506.05766/) (2025)
- [IA-T2I: Internet-Augmented Text-to-Image Generation](https://mlsanity.com/paper/2505.15779/) (2025)
- [QualiRAG: Retrieval-Augmented Generation for Visual Quality Understanding](https://mlsanity.com/paper/2601.18195/) (2026)
- [CityRAG: Stepping Into a City via Spatially-Grounded Video Generation](https://mlsanity.com/paper/2604.19741/) (2026)
- [When Looking Is Not Enough: Visual Attention Structure Reveals Hallucination in MLLMs](https://mlsanity.com/paper/2605.11559/) (2026)
- [Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual Generation](https://mlsanity.com/paper/2609.04282/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base](https://mlsanity.com/paper/2506.18856/) (2025)
- [Visual Personalization Turing Test](https://mlsanity.com/paper/2601.22680/) (2026)
- [ImageRAGTurbo: Towards One-step Text-to-Image Generation with Retrieval-Augmented Diffusion Models](https://mlsanity.com/paper/2602.12640/) (2026)
- [ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.03354/) (2026)
- [RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generation](https://mlsanity.com/paper/2606.17619/) (2026)
- [Reinforcing Egocentric Spatial Perception in Multimodal Large Language Models via Ego Scene Augmentation](https://mlsanity.com/paper/2607.14497/) (2026)
- [Dynamic Alignment Compensation for Hallucination Mitigation in Large Vision-Language Models](https://mlsanity.com/paper/2608.28058/) (2026)

## Abstract (arXiv)

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 knowledge. Furthermore, the real-object-based framework integrates fine-grained visual knowledge for the generative models, tackling the distortion problem and improving the realism for fine-grained object generation. Our Real-RAG is superior in its modular application to all types of state-of-the-art text-to-image generative models and also delivers remarkable performance boosts with all of them, such as a gain of 16.18% FID score with the auto-regressive model on the Stanford Car benchmark.