PortraitCraft: A Benchmark for Portrait Composition Understanding and Generation

• URL: http://arxiv.org/abs/2604.03611v1
• Date: Sat, 04 Apr 2026 06:50:51 GMT
• Title: PortraitCraft: A Benchmark for Portrait Composition Understanding and Generation
• Abstract summary: PortraitCraft is a unified benchmark for portrait composition understanding and generation.<n>PortraitCraft is built on a dataset of approximately 50,000 curated real portrait images.
• Score: 21.26852995282223
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The 1st PortraitCraft Challenge: A CVPR 2026 Workshop Competition on Portrait Composition Understanding and Generation [81.88187465365475]
  The PortraitCraft Challenge aims to advance AI research in portrait aesthetics analysis and controllable image synthesis.<n>To support the challenge, we constructed and publicly released a large-scale portrait composition dataset consisting of approximately 50,000 curated real portrait images.<n>This report describes the challenge setup, evaluation protocols, dataset composition, and final results, along with an analysis of the technical characteristics of the submitted solutions.
  arXiv  Detail & Related papers  (2026-06-09T14:05:48Z)
• Advancing Aesthetic Image Generation via Composition Transfer [57.624601729777986]
  Composer is a framework designed to model composition in a semantic-agnostic manner.<n>It supports composition transfer by extracting key composition-aware representations from a reference image.<n>It also supports theme-driven composition retrieval by leveraging the in-context learning capabilities of Large Vision-Language Models.
  arXiv  Detail & Related papers  (2026-05-06T07:56:16Z)
• A Sketch+Text Composed Image Retrieval Dataset for Thangka [14.600552992453977]
  Composed Image Retrieval (CIR) enables image retrieval by combining multiple query modalities.<n>CIRThan is a sketch+text Composed Image Retrieval dataset for Thangka imagery.
  arXiv  Detail & Related papers  (2026-02-09T09:14:29Z)
• Q-Bench-Portrait: Benchmarking Multimodal Large Language Models on Portrait Image Quality Perception [101.76154325436544]
  multimodal large language models (MLLMs) have demonstrated impressive performance on existing low-level vision benchmarks.<n>We introduce Q-Bench-Portrait, the first holistic benchmark specifically designed for portrait image quality perception.
  arXiv  Detail & Related papers  (2026-01-26T10:37:20Z)
• Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition [61.956088652094515]
  Vision and language models (VLMs) have showcased remarkable zero-shot recognition abilities. But they face challenges in visio-linguistic compositionality, particularly in linguistic comprehension and fine-grained image-text alignment. This paper explores the intricate relationship between compositionality and recognition.
  arXiv  Detail & Related papers  (2024-06-13T17:58:39Z)
• T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation [55.16845189272573]
  T2I-CompBench++ is an enhanced benchmark for compositional text-to-image generation.<n>It comprises 8,000 compositional text prompts categorized into four primary groups: attribute binding, object relationships, generative numeracy, and complex compositions.
  arXiv  Detail & Related papers  (2023-07-12T17:59:42Z)
• Portrait Interpretation and a Benchmark [49.484161789329804]
  The proposed portrait interpretation recognizes the perception of humans from a new systematic perspective. We construct a new dataset that contains 250,000 images labeled with identity, gender, age, physique, height, expression, and posture of the whole body and arms. Our experimental results demonstrate that combining the tasks related to portrait interpretation can yield benefits.
  arXiv  Detail & Related papers  (2022-07-27T06:25:09Z)
• StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis [52.341186561026724]
  Lacking compositionality could have severe implications for robustness and fairness. We introduce a new framework, StyleT2I, to improve the compositionality of text-to-image synthesis. Results show that StyleT2I outperforms previous approaches in terms of consistency between the input text and synthesized images.
  arXiv  Detail & Related papers  (2022-03-29T17:59:50Z)
• NPRportrait 1.0: A Three-Level Benchmark for Non-Photorealistic Rendering of Portraits [67.58044348082944]
  This paper proposes a new structured, three level, benchmark dataset for the evaluation of stylised portrait images. Rigorous criteria were used for its construction, and its consistency was validated by user studies. A new methodology has been developed for evaluating portrait stylisation algorithms.
  arXiv  Detail & Related papers  (2020-09-01T18:04:19Z)

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.