Layer-Aware Video Composition via Split-then-Merge
Abstract
A novel framework, Split-then-Merge, improves generative video composition through unsupervised learning of foreground-background interactions, achieving state-of-the-art performance.
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/VLLM-based qualitative evaluations. More details are available at our project page: https://split-then-merge.github.io
Community
🎥 Introducing Split-then-Merge: A new video composition framework!
This approach enables the composition of any foreground video with any background video.
Unlike conventional methods that rely on annotated datasets or handcrafted rules, Split-then-Merge (StM) splits a large unlabeled corpus of videos into dynamic foreground and background layers, then merges them to learn how dynamic subjects interact with diverse scenes.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- LayerComposer: Multi-Human Personalized Generation via Layered Canvas (2025)
- ID-Crafter: VLM-Grounded Online RL for Compositional Multi-Subject Video Generation (2025)
- Insert In Style: A Zero-Shot Generative Framework for Harmonious Cross-Domain Object Composition (2025)
- From Inpainting to Layer Decomposition: Repurposing Generative Inpainting Models for Image Layer Decomposition (2025)
- CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion (2025)
- Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset (2025)
- VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper