Multimodal Prediction and Personalization of Photo Edits with Deep Generative Models

TL;DR

This paper introduces a deep generative model for personalized photo editing suggestions that predicts diverse, high-quality edits and adapts to individual aesthetic preferences, improving over existing methods.

Contribution

The work presents a novel hierarchical neural network model that captures diverse editing styles and personalizes suggestions based on user preferences in photo editing.

Findings

Model outperforms existing approaches on multimodal prediction tasks.

Generates diverse and high-quality photo edit suggestions.

Learns and adapts to individual user aesthetic preferences.

Abstract

Professional-grade software applications are powerful but complicated$-$expert users can achieve impressive results, but novices often struggle to complete even basic tasks. Photo editing is a prime example: after loading a photo, the user is confronted with an array of cryptic sliders like "clarity", "temp", and "highlights". An automatically generated suggestion could help, but there is no single "correct" edit for a given image$-$different experts may make very different aesthetic decisions when faced with the same image, and a single expert may make different choices depending on the intended use of the image (or on a whim). We therefore want a system that can propose multiple diverse, high-quality edits while also learning from and adapting to a user's aesthetic preferences. In this work, we develop a statistical model that meets these objectives. Our model builds on recent advances in neural network generative modeling and scalable inference, and uses hierarchical structure to learn editing patterns across many diverse users. Empirically, we find that our model outperforms other approaches on this challenging multimodal prediction task.