MPJudge: Towards Perceptual Assessment of Music-Induced Paintings

TL;DR

This paper introduces MPJudge, a novel perceptual assessment framework for music-induced paintings, leveraging a large expert-annotated dataset and a fusion model to better evaluate artistic coherence beyond emotion-based methods.

Contribution

It presents MPD, a large-scale dataset with perceptual annotations, and MPJudge, a new model that directly assesses perceptual coherence between music and paintings.

Findings

MPJudge outperforms existing methods in perceptual assessment.

The dataset MPD enables more accurate training and evaluation.

Qualitative results show better identification of music-relevant regions.

Abstract

Music induced painting is a unique artistic practice, where visual artworks are created under the influence of music. Evaluating whether a painting faithfully reflects the music that inspired it poses a challenging perceptual assessment task. Existing methods primarily rely on emotion recognition models to assess the similarity between music and painting, but such models introduce considerable noise and overlook broader perceptual cues beyond emotion. To address these limitations, we propose a novel framework for music induced painting assessment that directly models perceptual coherence between music and visual art. We introduce MPD, the first large scale dataset of music painting pairs annotated by domain experts based on perceptual coherence. To better handle ambiguous cases, we further collect pairwise preference annotations. Building on this dataset, we present MPJudge, a model that integrates music features into a visual encoder via a modulation based fusion mechanism. To effectively learn from ambiguous cases, we adopt Direct Preference Optimization for training. Extensive experiments demonstrate that our method outperforms existing approaches. Qualitative results further show that our model more accurately identifies music relevant regions in paintings.