Aesthetic Photo Collage with Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach for automatic photo collage generation that optimizes aesthetic quality by modeling layout as a sequential decision process, overcoming data limitations with pretraining.

Contribution

It is the first to apply reinforcement learning to collage layout optimization and integrates a pretraining strategy with an attention fusion module for aesthetic assessment.

Findings

Outperforms existing methods in aesthetic quality evaluation.

Successfully models collage as a sequential decision process.

User studies confirm improved aesthetic appeal.

Abstract

Photo collage aims to automatically arrange multiple photos on a given canvas with high aesthetic quality. Existing methods are based mainly on handcrafted feature optimization, which cannot adequately capture high-level human aesthetic senses. Deep learning provides a promising way, but owing to the complexity of collage and lack of training data, a solution has yet to be found. In this paper, we propose a novel pipeline for automatic generation of aspect ratio specified collage and the reinforcement learning technique is introduced in collage for the first time. Inspired by manual collages, we model the collage generation as sequential decision process to adjust spatial positions, orientation angles, placement order and the global layout. To instruct the agent to improve both the overall layout and local details, the reward function is specially designed for collage, considering subjective and objective factors. To overcome the lack of training data, we pretrain our deep aesthetic network on a large scale image aesthetic dataset (CPC) for general aesthetic feature extraction and propose an attention fusion module for structural collage feature representation. We test our model against competing methods on two movie datasets and our results outperform others in aesthetic quality evaluation. Further user study is also conducted to demonstrate the effectiveness.