cs.CLMar 6, 2026

The Art That Poses Back: Assessing AI Pastiches after Contemporary Artworks

Authors: Anca Dinu, Andreiana Mihail, Andra-Maria Florescu, Claudiu Creanga

Organizations: University of Bucharest, ISDS, 90 Panduri Road, Bucharest, 050107, Romania

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

This study explores artificial visual creativity, focusing on ChatGPT's ability to generate new images intentionally pastiching original artworks such as paintings, drawings, sculptures and installations. The process involved twelve artists from Romania, Bulgaria, France, Austria, and the United Kingdom, each invited to contribute with three of their artworks and to grade and comment on the AI-generated versions. The analysis combines human evaluation with computational methods aimed at detecting visual and stylistic similarities or divergences between the original works and their AI-produced renditions. The results point to a significant gap between color and texture-based similarity and compositional, conceptual, and perceptual one. Consequently, we advocate for the use of a "style transfer dashboard" of complementary metrics to evaluate the similarity between pastiches and originals, rather than using a single style metric. The artists' comments revealed limitations of ChatGPT's pastiches after contemporary artworks, which were perceived by the authors of the originals as lacking dimensionality, context, and intentional sense, and seeming more of a paraphrase or an approximate quotation rather than as a valuable, emotion-evoking artwork.

Figures & tables

ModelOrg →\rightarrow Pst1Org →\rightarrow Pst2AveragePst1 ↔\leftrightarrow Pst2Feature type
AdaIN-Style0.0550.0710.0630.068texture, color
CLIP-ViT-L0.1940.2000.1970.173conceptual
ResNet50-Style0.4270.4810.4540.402artistic style
DINOv20.4410.4840.4630.396fine-grained visual
VGG190.6480.7010.6740.662perceptual
Table 1: Average Cosine Distances by Model. Lower values (the lowest in bold) indicate higher similarity. AdaIN-Style is the most forgiving, while VGG19 is the strictest.
Figure 1: Bar charts comparing average cosine distances for Orig →\rightarrow Past1, Orig →\rightarrow Past2, and Past1 ↔\leftrightarrow Past2 comparisons across all five models.
Figure 2: Distance distributions for each of the five models. Note the tight, low-distance grouping of AdaIN-Style versus the wide, high-distance spread of DINOv2 and VGG19, illustrating their respective discrimination power.
ModelVarianceDiscriminationPastichesConsistency
   (Avg. Diff.) 
DINOv20.0349Most Discriminative0.131Most Variable
VGG190.0274High Discrimination0.111Moderate
ResNet50-Style0.0249Balanced0.115Moderate
CLIP-ViT-L0.0103Consistent0.046Very Consistent
AdaIN-Style0.0014Least Discriminative0.034Most Consistent
Table 2: Model Discrimination (Variance) and Pastiche Consistency. Discrimination measures the spread of all measurements, while Consistency measures the average difference between the two pastiche distances for the same artwork.
Figure 3: We computed pairwise correlations to see if models that rank one pastiche as very similar to the original (low distance) also rank others similarly. This scatter plots visualize the agreement for all model pairs.
Figure 4: Visual example of the “Compositional Gap” (High DINO, Low AdaIN). This case illustrates pastiches that successfully mimic the texture and color palette of the original (low AdaIN distance) but fail to capture the structural composition (high DINO distance).
Figure 5: Visual example of Structural Alignment (Low DINO, High AdaIN). Representing the inverse of the “Compositional Gap,” this case shows where the AI successfully replicates the spatial composition and geometric blocking (low DINO distance) but deviates in texture or color statistics.
Figure 6: Artists’ Graded Perception of ChatGPT’s pastiches after their works.
Figure 7: Ion Grigorescu’s artwork Măriuca versus its Pastiche 1.
Figure 8: Tom Chamberlain’s artwork Dimmer versus its Pastiche 1.
Figure 9: Philip Patkowitsch’s artwork Untitled versus its Pastiche 2.
More in this topic

Image Generation

Image generation studies models that create or edit images from text, examples, layouts, and other structured controls.

See all 463 papers

Explore similar work

CardsList

  1. Back to Back with a Copy: A Computational Analysis of AI-Generated Visual Contemporary Art Pastiches

    Jul 22, 2026Anca Dinu, Andreiana Mihail, Andra-Maria Florescu +2StylometryImage Generation Evaluation

    University of Bucharest, Bucharest, Romania

  2. Measuring Similarity between Artistic and AI Generated Images using Siamese Neural Networks

    Aug 24, 2026Diego Castro Elvira, Navil Pineda Rugerio, Jesús García-Ramírez +2AI-Generated Image Detection

    UPIIT, Instituto Politécnico Nacional Guillermo Valle 11, Centro, C.P. 90000 Tlaxcala de Xicohténcatl, Tlaxcala, Mexico.

  3. The Silent Brush: Evaluating Artistic Style Leakage in AI Art Generation

    May 17, 2026Ninad Joshi, Ashutosh Ranjan, Vivek Srivastava +1T2I GenerationT2I Generation Evaluation

    TCS Research, India