Layer-Aware Video Composition via Split-then-Merge

arXiv:2511.20809v2 Announce Type: replace Abstract: We present Split-then-Merge (StM), a novel framework designed to enhance control in generative video composition and address its data scarcity problem. Unlike conventional methods relying on annotated datasets or handcrafted rules, StM splits a large corpus of unlabeled videos into dynamic foreground and background layers, then self-composes them to learn how dynamic subjects interact with diverse scenes. This process enables the model to learn the complex compositional dynamics required for realistic video generation. StM introduces a novel transformation-aware training pipeline that utilizes a multi-layer fusion and augmentation to achieve affordance-aware composition, alongside an identity-preservation loss that maintains foreground fidelity during blending. Experiments show StM outperforms SoTA methods in both quantitative benchmarks and in humans/VLM-based qualitative evaluations. More details are available at our project page: https://split-then-merge.github.io

Related

• CamC2V: Context-aware Controllable Video Generation
• Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting
• Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation

Source: arXiv cs.CV | 2026-08-26