# Modeling and Forecasting Art Movements with CGANs

## TL;DR

This paper introduces a method to train CGANs conditioned on sequences of continuous distributions, enabling the generation and forecasting of art movements' evolution through a combination of generative modeling and time series prediction.

## Contribution

We propose a novel training approach for CGANs that conditions on sequences of continuous distributions, allowing for the prediction of future art movements and their generated artworks.

## Key findings

- Accurately predicts future art movement distributions.
- Generates plausible future paintings based on learned distributions.
- Small mean distance between predictions and actual art movements.

## Abstract

Conditional Generative Adversarial Networks~(CGAN) are a recent and popular method for generating samples from a probability distribution conditioned on latent information. The latent information often comes in the form of a discrete label from a small set. We propose a novel method for training CGANs which allows us to condition on a sequence of continuous latent distributions $f^{(1)}, \ldots, f^{(K)}$. This training allows CGANs to generate samples from a sequence of distributions. We apply our method to paintings from a sequence of artistic movements, where each movement is considered to be its own distribution. Exploiting the temporal aspect of the data, a vector autoregressive (VAR) model is fitted to the means of the latent distributions that we learn, and used for one-step-ahead forecasting, to predict the latent distribution of a future art movement $f^{{(K+1)}}$. Realisations from this distribution can be used by the CGAN to generate "future" paintings. In experiments, this novel methodology generates accurate predictions of the evolution of art. The training set consists of a large dataset of past paintings. While there is no agreement on exactly what current art period we find ourselves in, we test on plausible candidate sets of present art, and show that the mean distance to our predictions is small.