# PortraitCraft: A Benchmark for Portrait Composition Understanding and Generation

arXiv: https://arxiv.org/abs/2604.03611 · HTML: https://mlsanity.com/paper/2604.03611/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 4 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Photo Aesthetics Ranking Network with Attributes and Content Adaptation](https://mlsanity.com/paper/1606.01621/) (2016)
- [UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics](https://mlsanity.com/paper/2412.07774/) (2024)
- [Personalized Image Aesthetics Assessment with Rich Attributes](https://mlsanity.com/paper/2203.16754/) (2022)
- [ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving](https://mlsanity.com/paper/2404.16771/) (2024)
- [ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding](https://mlsanity.com/paper/2507.14533/) (2025)
- [EchoShot: Multi-Shot Portrait Video Generation](https://mlsanity.com/paper/2506.15838/) (2025)
- [FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity](https://mlsanity.com/paper/2411.15411/) (2024)
- [Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought](https://mlsanity.com/paper/2505.23766/) (2025)
- [APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments](https://mlsanity.com/paper/2411.08545/) (2024)
- [LAPIS: A novel dataset for personalized image aesthetic assessment](https://mlsanity.com/paper/2504.07670/) (2025)
- [Science-T2I: Addressing Scientific Illusions in Image Synthesis](https://mlsanity.com/paper/2504.13129/) (2025)
- [An Image Quality Assessment Dataset for Portraits](https://mlsanity.com/paper/2304.05772/) (2023)
- [HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis](https://mlsanity.com/paper/2503.16944/) (2025)
- [HiFi-Portrait: Zero-shot Identity-preserved Portrait Generation with High-fidelity Multi-face Fusion](https://mlsanity.com/paper/2512.14542/) (2025)
- [MDD-LLM: Towards Accuracy Large Language Models for Major Depressive Disorder Diagnosis](https://mlsanity.com/paper/2505.00032/) (2025)

## Built on by (most cited first, 1 of 1)

- [PortraitAes: Intent-Conditioned Structured Portrait Aesthetic Assessment](https://mlsanity.com/paper/2610.05010/) (2026)

## Abstract (arXiv)

Portrait composition plays a central role in portrait aesthetics and visual communication, yet existing datasets and benchmarks mainly focus on coarse aesthetic scoring, generic image aesthetics, or unconstrained portrait generation. This limits systematic research on structured portrait composition analysis and controllable portrait generation under explicit composition requirements. In this paper, we introduce PortraitCraft, a unified benchmark for portrait composition understanding and generation. PortraitCraft is built on a dataset of approximately 50,000 curated real portrait images with structured multi-level supervision, including global composition scores, annotations over 13 composition attributes, attribute-level explanation texts, visual question answering pairs, and composition-oriented textual descriptions for generation. Based on this dataset, we establish two complementary benchmark tasks for composition understanding and composition-aware generation within a unified framework. The first evaluates portrait composition understanding through score prediction, fine-grained attribute reasoning, and image-grounded visual question answering, while the second evaluates portrait generation from structured composition descriptions under explicit composition constraints. We further define standardized evaluation protocols and provide reference baseline results with representative multimodal models. PortraitCraft provides a comprehensive benchmark for future research on fine-grained portrait understanding, interpretable aesthetic assessment, and controllable portrait generation.