Generating long-horizon music videos (MVs) is frequently constrained by prohibitive computational costs and difficulty maintaining cross-shot consistency. We propose AllocMV, a hierarchical framework formulating music video synthesis as a Multiple-Choice Knapsack Problem (MCKP). AllocMV represents the video's persistent state as a compact, structured object comprising character entities, scene priors, and sharing graphs, produced by a global planner prior to realization. By estimating segment saliency from multimodal cues, a group-level MCKP solver based on dynamic programming optimally allocates resources across High-Gen, Mid-Gen, and Reuse branches. For repetitive musical motifs, we implement a divergence-based forking strategy that reuses visual prefixes to reduce costs while ensuring motif-level continuity. Evaluated via the Cost-Quality Ratio (CQR), AllocMV achieves an optimal trade-off between perceived quality and resource expenditure under strict budgetary and rhythmic constraints.
Cite
@article{arxiv.2605.10723,
title = {AllocMV: Optimal Resource Allocation for Music Video Generation via Structured Persistent State},
author = {Huimin Wang and Leilei Ouyang and Chang Xia and Yongqi Kang and Yu Fu and Yuqi Ouyang},
journal= {arXiv preprint arXiv:2605.10723},
year = {2026}
}