ShutterMuse: Capture-Time Photography Guidance with MLLMs

• URL: http://arxiv.org/abs/2606.25763v1
• Date: Wed, 24 Jun 2026 12:37:56 GMT
• Title: ShutterMuse: Capture-Time Photography Guidance with MLLMs
• Abstract summary: Real-world photography requires capture-time guidance for both camera framing and subject pose.<n>Existing aesthetic cropping benchmarks mainly evaluate post-hoc crop prediction and overlook subject-side recommendations.<n>We introduce CaptureGuide-Bench, a benchmark with two complementary tasks: photographer-side composition decision and refinement, and subject-side scene-conditioned pose recommendation.
• Score: 39.02235069316064
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet existing aesthetic cropping benchmarks mainly evaluate post-hoc crop prediction and overlook subject-side recommendations, leaving the capture-time guidance capabilities of multimodal large language models (MLLMs) underexplored. To address this gap, we introduce CaptureGuide-Bench, a benchmark with two complementary tasks: photographer-side composition decision and refinement, and subject-side scene-conditioned pose recommendation. Our evaluation reveals limitations: general-purpose MLLMs can make composition decisions but lack precise refinement localization, while specialized aesthetic cropping models localize crops effectively but are limited to refinement; neither provides actionable pose guidance. To support model development, we further construct CaptureGuide-Dataset, comprising 130K samples with textual rationales and structured visual annotations, and develop ShutterMuse, a unified MLLM trained with supervised and reinforcement fine-tuning. Experiments on CaptureGuide-Bench show that ShutterMuse achieves the best overall photographer-side performance among evaluated baselines and competitive subject-side pose recommendation with substantially lower inference cost, demonstrating the potential of MLLMs as interactive assistants for photography during image capture.

Related papers

• Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping [47.103757942619914]
  Smartphones have made photography ubiquitous, yet a clear gap remains between ordinary users and professional photographers.<n>We define aesthetic guidance (AG) as an essential but largely underexplored domain in computational aesthetics.<n>We introduce AesGuide, the first large-scale AG dataset and benchmark with 10,748 photos annotated with aesthetic scores, analyses, and guidance.<n>We propose Venus, a two-stage framework that first empowers MLLMs with AG capability through progressively complex aesthetic questions.
  arXiv  Detail & Related papers  (2026-02-27T12:47:31Z)
• RetouchIQ: MLLM Agents for Instruction-Based Image Retouching with Generalist Reward [64.78078130943489]
  We introduce RetouchIQ, a framework that performs instruction-based executable image editing through MLLM agents guided by a reward model.<n>We show that RetouchIQ substantially improves both semantic consistency and perceptual quality over previous MLLM-based and diffusion-based editing systems.
  arXiv  Detail & Related papers  (2026-02-19T17:11:59Z)
• SQUARE: Semantic Query-Augmented Fusion and Efficient Batch Reranking for Training-free Zero-Shot Composed Image Retrieval [2.624097337766623]
  Composed Image Retrieval (CIR) aims to retrieve target images that preserve the visual content of a reference image while incorporating user-specified textual modifications.<n>We present a novel two-stage training-free framework that leverages Multimodal Large Language Models (MLLMs) to enhance ZS-CIR.
  arXiv  Detail & Related papers  (2025-09-30T14:41:24Z)
• LVLM-Composer's Explicit Planning for Image Generation [0.0]
  We introduce LVLM-Composer, a novel 10-billion parameter scale LVLM specifically engineered for enhanced compositional image synthesis.<n>Our method incorporates a Hierarchical Semantic Planning Module for structured prompt decomposition and a Fine-Grained Feature Alignment Mechanism for precise visual guidance during generation.<n>Experiments on the LongBench-T2I benchmark, utilizing automatic evaluation by Gemini-2.0-Flash and InternVL3-78B, demonstrate LVLM-Composer's superior performance across critical compositional dimensions.
  arXiv  Detail & Related papers  (2025-07-05T20:21:03Z)
• ProCrop: Learning Aesthetic Image Cropping from Professional Compositions [57.949730056500634]
  ProCrop is a retrieval-based method that leverages professional photography to guide cropping decisions.<n>We present a large-scale dataset of 242K weakly-annotated images, generated by out-painting professional images.<n>This composition-aware dataset generation offers diverse high-quality crop proposals guided by aesthetic principles.
  arXiv  Detail & Related papers  (2025-05-28T15:38:44Z)
• CameraBench: Benchmarking Visual Reasoning in MLLMs via Photography [12.305953690308085]
  Large language models (LLMs) and multimodal large language models (MLLMs) have significantly advanced artificial intelligence.<n>Recent advancements, including the reasoning models like OpenAI o1 and Gemini 2.0 Flash Thinking, have opened this capability.<n>We focus specifically on photography-related tasks because a photo is a visual snapshot of the physical world where the underlying physics interplay with the camera parameters.
  arXiv  Detail & Related papers  (2025-04-14T10:53:44Z)
• Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning [56.31096024472269]
  We introduce DeCapBench along with a novel metric, DCScore, specifically designed for detailed captioning tasks.<n>DCScore evaluates hallucinations and fine-grained comprehensiveness by deconstructing responses into the smallest self-sufficient units.<n>DeCapBench exhibits a high correlation with VLM arena results on descriptive tasks, surpassing existing benchmarks for vision-language models.
  arXiv  Detail & Related papers  (2025-03-10T22:53:56Z)
• Cropper: Vision-Language Model for Image Cropping through In-Context Learning [54.34593968212081]
  We propose an effective approach to leverage large vision-language models (VLMs) for image cropping.<n>First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples.<n>Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops.<n>The proposed framework, we refer to as Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping.
  arXiv  Detail & Related papers  (2024-08-14T20:03:03Z)
• Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning [93.6645991946674]
  We introduce panoramic panoptic segmentation, as the most holistic scene understanding. A complete surrounding understanding provides a maximum of information to a mobile agent. We propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain.
  arXiv  Detail & Related papers  (2022-06-21T20:07:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.