Aesthetic Photo Collage with Deep Reinforcement Learning
This addresses the challenge of creating high-quality photo collages for applications like digital media and design, though it is an incremental improvement by introducing reinforcement learning to a domain previously dominated by handcrafted methods.
The paper tackled the problem of automatically arranging multiple photos into aesthetically pleasing collages by proposing a deep reinforcement learning pipeline that models collage generation as a sequential decision process, and it outperformed competing methods in aesthetic quality evaluations on movie datasets.
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.