MPJudge: Towards Perceptual Assessment of Music-Induced Paintings
This addresses a challenging perceptual assessment task in music-induced painting, offering a more accurate evaluation method for artists and researchers, though it is incremental in improving upon emotion-based approaches.
The paper tackles the problem of evaluating whether paintings faithfully reflect the music that inspired them, proposing a novel framework that directly models perceptual coherence and outperforms existing methods.
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.