Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AI
- URL: http://arxiv.org/abs/2502.05999v1
- Date: Sun, 09 Feb 2025 19:02:32 GMT
- Title: Pencils to Pixels: A Systematic Study of Creative Drawings across Children, Adults and AI
- Authors: Surabhi S Nath, Guiomar del Cuvillo y Schröder, Claire E. Stevenson,
- Abstract summary: We analyze 1338 drawings by children, adults and AI on a creative drawing task.
For style, we define measures of ink density, ink distribution and number of elements.
For content, we use expert-annotated categories to study conceptual diversity.
We build simple models to predict expert and automated creativity scores.
- Score: 0.0
- License:
- Abstract: Can we derive computational metrics to quantify visual creativity in drawings across intelligent agents, while accounting for inherent differences in technical skill and style? To answer this, we curate a novel dataset consisting of 1338 drawings by children, adults and AI on a creative drawing task. We characterize two aspects of the drawings -- (1) style and (2) content. For style, we define measures of ink density, ink distribution and number of elements. For content, we use expert-annotated categories to study conceptual diversity, and image and text embeddings to compute distance measures. We compare the style, content and creativity of children, adults and AI drawings and build simple models to predict expert and automated creativity scores. We find significant differences in style and content in the groups -- children's drawings had more components, AI drawings had greater ink density, and adult drawings revealed maximum conceptual diversity. Notably, we highlight a misalignment between creativity judgments obtained through expert and automated ratings and discuss its implications. Through these efforts, our work provides, to the best of our knowledge, the first framework for studying human and artificial creativity beyond the textual modality, and attempts to arrive at the domain-agnostic principles underlying creativity. Our data and scripts are available on GitHub.
Related papers
- Expertise elevates AI usage: experimental evidence comparing laypeople and professional artists [1.5296069874080693]
We compare the artistic capabilities of artists and laypeople using generative AI.
On average, artists produced more faithful and creative outputs than their lay counterparts.
While AI may ease content creation, professional expertise is still valuable.
arXiv Detail & Related papers (2025-01-21T18:53:21Z) - GalleryGPT: Analyzing Paintings with Large Multimodal Models [64.98398357569765]
Artwork analysis is important and fundamental skill for art appreciation, which could enrich personal aesthetic sensibility and facilitate the critical thinking ability.
Previous works for automatically analyzing artworks mainly focus on classification, retrieval, and other simple tasks, which is far from the goal of AI.
We introduce a superior large multimodal model for painting analysis composing, dubbed GalleryGPT, which is slightly modified and fine-tuned based on LLaVA architecture.
arXiv Detail & Related papers (2024-08-01T11:52:56Z) - ORACLE: Leveraging Mutual Information for Consistent Character Generation with LoRAs in Diffusion Models [3.7599363231894185]
We introduce a novel framework designed to produce consistent character representations from a single text prompt.
Our framework outperforms existing methods in generating characters with consistent visual identities.
arXiv Detail & Related papers (2024-06-04T23:39:08Z) - DreamCreature: Crafting Photorealistic Virtual Creatures from
Imagination [140.1641573781066]
We introduce a novel task, Virtual Creatures Generation: Given a set of unlabeled images of the target concepts, we aim to train a T2I model capable of creating new, hybrid concepts.
We propose a new method called DreamCreature, which identifies and extracts the underlying sub-concepts.
The T2I thus adapts to generate novel concepts with faithful structures and photorealistic appearance.
arXiv Detail & Related papers (2023-11-27T01:24:31Z) - SketchDreamer: Interactive Text-Augmented Creative Sketch Ideation [111.2195741547517]
We present a method to generate controlled sketches using a text-conditioned diffusion model trained on pixel representations of images.
Our objective is to empower non-professional users to create sketches and, through a series of optimisation processes, transform a narrative into a storyboard.
arXiv Detail & Related papers (2023-08-27T19:44:44Z) - A Method for Animating Children's Drawings of the Human Figure [9.076663874652725]
We present a system that automatically animates children's drawings of the human figure.
We demonstrate the value and broad appeal of our approach by building and releasing the Animated Drawings Demo.
arXiv Detail & Related papers (2023-03-07T22:31:28Z) - Automatic Creativity Measurement in Scratch Programs Across Modalities [6.242018846706069]
We make the journey fromdefining a formal measure of creativity that is efficientlycomputable to applying the measure in a practical domain.
We adapted the general measure for projects in the popular visual programming language Scratch.
We designed a machine learning model for predicting the creativity of Scratch projects, trained and evaluated on human expert creativity assessments.
arXiv Detail & Related papers (2022-11-07T10:43:36Z) - DoodleFormer: Creative Sketch Drawing with Transformers [68.18953603715514]
Creative sketching or doodling is an expressive activity, where imaginative and previously unseen depictions of everyday visual objects are drawn.
Here, we propose a novel coarse-to-fine two-stage framework, DoodleFormer, that decomposes the creative sketch generation problem into the creation of coarse sketch composition.
To ensure diversity of the generated creative sketches, we introduce a probabilistic coarse sketch decoder.
arXiv Detail & Related papers (2021-12-06T18:59:59Z) - Telling Creative Stories Using Generative Visual Aids [52.623545341588304]
We asked writers to write creative stories from a starting prompt, and provided them with visuals created by generative AI models from the same prompt.
Compared to a control group, writers who used the visuals as story writing aid wrote significantly more creative, original, complete and visualizable stories.
Findings indicate that cross modality inputs by AI can benefit divergent aspects of creativity in human-AI co-creation, but hinders convergent thinking.
arXiv Detail & Related papers (2021-10-27T23:13:47Z) - Creative Sketch Generation [48.16835161875747]
We introduce two datasets of creative sketches -- Creative Birds and Creative Creatures -- containing 10k sketches each along with part annotations.
We propose DoodlerGAN -- a part-based Generative Adrial Network (GAN) -- to generate unseen compositions of novel part appearances.
Quantitative evaluations as well as human studies demonstrate that sketches generated by our approach are more creative and of higher quality than existing approaches.
arXiv Detail & Related papers (2020-11-19T18:57:00Z)
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.