# Retrieval-Augmented Perception: High-Resolution Image Perception Meets Visual RAG

arXiv: https://arxiv.org/abs/2503.01222 · HTML: https://mlsanity.com/paper/2503.01222/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 40 of its 47 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)
- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 40)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites](https://mlsanity.com/paper/2404.16821/) (2024)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models](https://mlsanity.com/paper/2403.18814/) (2024)
- [Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models](https://mlsanity.com/paper/2311.06607/) (2023)
- [MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?](https://mlsanity.com/paper/2408.13257/) (2024)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding](https://mlsanity.com/paper/2403.18715/) (2024)
- [Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2408.15556/) (2024)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Automatic Spatially-aware Fashion Concept Discovery](https://mlsanity.com/paper/1708.01311/) (2017)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models](https://mlsanity.com/paper/2403.03003/) (2024)
- [WebQA: Multihop and Multimodal QA](https://mlsanity.com/paper/2109.00590/) (2021)
- [ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration](https://mlsanity.com/paper/2411.16044/) (2024)
- [MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models](https://mlsanity.com/paper/2410.13085/) (2024)
- [Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models](https://mlsanity.com/paper/2312.06109/) (2023)

## Built on by (most cited first, 23 of 23)

- [Look Where It Matters: Training-Free Ultra-HR Remote Sensing VQA via Adaptive Zoom Search](https://mlsanity.com/paper/2511.20460/) (2025)
- [Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation](https://mlsanity.com/paper/2510.20812/) (2025)
- [What, Whether and How? Unveiling Process Reward Models for Thinking with Images Reasoning](https://mlsanity.com/paper/2602.08346/) (2026)
- [AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders](https://mlsanity.com/paper/2505.24519/) (2025)
- [OmniRAG-Agent: Agentic Omnimodal Reasoning for Low-Resource Long Audio-Video Question Answering](https://mlsanity.com/paper/2602.03707/) (2026)
- [Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception](https://mlsanity.com/paper/2505.23275/) (2025)
- [BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions](https://mlsanity.com/paper/2506.05766/) (2025)
- [The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design](https://mlsanity.com/paper/2605.01345/) (2026)
- [Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective](https://mlsanity.com/paper/2511.14772/) (2025)
- [MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding](https://mlsanity.com/paper/2512.02906/) (2025)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [Self-Prophetic Decoding to Unlock Visual Search in LVLMs](https://mlsanity.com/paper/2605.28741/) (2026)
- [ActiveScope: Actively Seeking and Correcting Perception for MLLMs](https://mlsanity.com/paper/2606.24292/) (2026)
- [Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation](https://mlsanity.com/paper/2509.26277/) (2025)
- [LITTA: Late-Interaction and Test-Time Alignment for Visually-Grounded Multimodal Retrieval](https://mlsanity.com/paper/2603.26683/) (2026)
- [Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding](https://mlsanity.com/paper/2606.16158/) (2026)
- [Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG](https://mlsanity.com/paper/2606.21968/) (2026)
- [Towards High-Resolution Visual Perception via Hierarchical Entity Exploration](https://mlsanity.com/paper/2607.00816/) (2026)
- [BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception](https://mlsanity.com/paper/2607.03184/) (2026)
- [VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents](https://mlsanity.com/paper/2607.24748/) (2026)
- [Zero-MELO: Test-Time Evidence Calibration with Multimodal LLMs for Zero-Shot Micro-Gesture Recognition](https://mlsanity.com/paper/2608.14854/) (2026)
- [The Earth in One Gaze: Training-Free Active Focus for UHR Remote Sensing Understanding](https://mlsanity.com/paper/2609.31747/) (2026)
- [Not All Error Yields to Scale: Where Scaling Stops in Vision-Language Inference](https://mlsanity.com/paper/2610.01640/) (2026)

## Abstract (arXiv)

High-resolution (HR) image perception remains a key challenge in multimodal large language models (MLLMs). To overcome the limitations of existing methods, this paper shifts away from prior dedicated heuristic approaches and revisits the most fundamental idea to HR perception by enhancing the long-context capability of MLLMs, driven by recent advances in long-context techniques like retrieval-augmented generation (RAG) for general LLMs. Towards this end, this paper presents the first study exploring the use of RAG to address HR perception challenges. Specifically, we propose Retrieval-Augmented Perception (RAP), a training-free framework that retrieves and fuses relevant image crops while preserving spatial context using the proposed Spatial-Awareness Layout. To accommodate different tasks, the proposed Retrieved-Exploration Search (RE-Search) dynamically selects the optimal number of crops based on model confidence and retrieval scores. Experimental results on HR benchmarks demonstrate the significant effectiveness of RAP, with LLaVA-v1.5-13B achieving a 43% improvement on V^* Bench and 19% on HR-Bench.