AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning

TL;DR

AutoPhoto introduces a reinforcement learning-based system that autonomously navigates indoor environments to capture aesthetically pleasing photos, leveraging a learned aesthetics metric instead of traditional heuristics.

Contribution

It presents the first autonomous system capable of exploring environments and capturing aesthetic photos using a data-driven aesthetics estimator and reinforcement learning.

Findings

System successfully captures aesthetic photos in simulation.

System effectively captures aesthetic photos in real-world environments.

First to automate environment exploration for aesthetic photography.

Abstract

The process of capturing a well-composed photo is difficult and it takes years of experience to master. We propose a novel pipeline for an autonomous agent to automatically capture an aesthetic photograph by navigating within a local region in a scene. Instead of classical optimization over heuristics such as the rule-of-thirds, we adopt a data-driven aesthetics estimator to assess photo quality. A reinforcement learning framework is used to optimize the model with respect to the learned aesthetics metric. We train our model in simulation with indoor scenes, and we demonstrate that our system can capture aesthetic photos in both simulation and real world environments on a ground robot. To our knowledge, this is the first system that can automatically explore an environment to capture an aesthetic photo with respect to a learned aesthetic estimator.