Efficient Visual Appearance Optimization by Learning from Prior Preferences

TL;DR

Meta-PO combines preference-based Bayesian optimization with meta-learning to efficiently personalize visual appearance adjustments, significantly reducing the number of iterations needed for users to achieve desired results.

Contribution

The paper introduces Meta-PO, a novel approach that leverages prior user preferences via meta-learning to enhance sample efficiency in visual appearance optimization.

Findings

Meta-PO achieves satisfactory results in approximately 6 iterations for similar user goals.

Meta-PO generalizes across divergent preferences, reaching results in about 8 iterations.

The method improves personalization efficiency, making visual optimization more accessible for end-users.

Abstract

Adjusting visual parameters such as brightness and contrast is common in our everyday experiences. Finding the optimal parameter setting is challenging due to the large search space and the lack of an explicit objective function, leaving users to rely solely on their implicit preferences. Prior work has explored Preferential Bayesian Optimization (PBO) to address this challenge, involving users to iteratively select preferred designs from candidate sets. However, PBO often requires many rounds of preference comparisons, making it more suitable for designers than everyday end-users. We propose Meta-PO, a novel method that integrates PBO with meta-learning to improve sample efficiency. Specifically, Meta-PO infers prior users' preferences and stores them as models, which are leveraged to intelligently suggest design candidates for the new users, enabling faster convergence and more personalized results. An experimental evaluation of our method for appearance design tasks on 2D and 3D content showed that participants achieved satisfactory appearance in 5.86 iterations using Meta-PO when participants shared similar goals with a population (e.g., tuning for a ``warm'' look) and in 8 iterations even generalizes across divergent goals (e.g., from ``vintage'', ``warm'', to ``holiday''). Meta-PO makes personalized visual optimization more applicable to end-users through a generalizable, more efficient optimization conditioned on preferences, with the potential to scale interface personalization more broadly.