# Venus: Benchmarking and Empowering Multimodal Large Language Models for Aesthetic Guidance and Cropping

arXiv: https://arxiv.org/abs/2602.23980 · HTML: https://mlsanity.com/paper/2602.23980/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 36 of its 58 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 30 of 36)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future](https://mlsanity.com/paper/2309.15402/) (2023)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception](https://mlsanity.com/paper/2401.08276/) (2024)
- [Personalized Image Aesthetics Assessment with Rich Attributes](https://mlsanity.com/paper/2203.16754/) (2022)
- [AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception](https://mlsanity.com/paper/2404.09624/) (2024)
- [UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark](https://mlsanity.com/paper/2404.09619/) (2024)
- [ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding](https://mlsanity.com/paper/2507.14533/) (2025)
- [Reliable and Efficient Image Cropping: A Grid Anchor based Approach](https://mlsanity.com/paper/1904.04441/) (2019)
- [Quantitative Analysis of Automatic Image Cropping Algorithms: A Dataset and Comparative Study](https://mlsanity.com/paper/1701.01480/) (2017)
- [Grid Anchor based Image Cropping: A New Benchmark and An Efficient Model](https://mlsanity.com/paper/1909.08989/) (2019)
- [Image Cropping with Composition and Saliency Aware Aesthetic Score Map](https://mlsanity.com/paper/1911.10492/) (2019)
- [Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation](https://mlsanity.com/paper/2510.08673/) (2025)
- [APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments](https://mlsanity.com/paper/2411.08545/) (2024)
- [Multimodal LLMs Can Reason about Aesthetics in Zero-Shot](https://mlsanity.com/paper/2501.09012/) (2025)
- [Spatial-Semantic Collaborative Cropping for User Generated Content](https://mlsanity.com/paper/2401.08086/) (2024)

## Built on by (most cited first, 5 of 5)

- [ShutterMuse: Capture-Time Photography Guidance with MLLMs](https://mlsanity.com/paper/2606.25763/) (2026)
- [COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping](https://mlsanity.com/paper/2608.07570/) (2026)
- [AUV-Bench: Aesthetic Understanding and Generation Evaluation for User Interfaces](https://mlsanity.com/paper/2609.34854/) (2026)
- [Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping](https://mlsanity.com/paper/2610.00582/) (2026)
- [FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model](https://mlsanity.com/paper/2610.17639/) (2026)

## Abstract (arXiv)

The widespread use of smartphones has made photography ubiquitous, yet a clear gap remains between ordinary users and professional photographers, who can identify aesthetic issues and provide actionable shooting guidance during capture. We define this capability as aesthetic guidance (AG) -- an essential but largely underexplored domain in computational aesthetics. Existing multimodal large language models (MLLMs) primarily offer overly positive feedback, failing to identify issues or provide actionable guidance. Without AG capability, they cannot effectively identify distracting regions or optimize compositional balance, thus also struggling in aesthetic cropping, which aims to refine photo composition through reframing after capture. To address this, we introduce AesGuide, the first large-scale AG dataset and benchmark with 10,748 photos annotated with aesthetic scores, analyses, and guidance. Building upon it, we propose Venus, a two-stage framework that first empowers MLLMs with AG capability through progressively complex aesthetic questions and then activates their aesthetic cropping power via CoT-based rationales. Extensive experiments show that Venus substantially improves AG capability and achieves state-of-the-art (SOTA) performance in aesthetic cropping, enabling interpretable and interactive aesthetic refinement across both stages of photo creation. Code is available at https://github.com/PKU-ICST-MIPL/Venus_CVPR2026.