Saved in:
Bibliographic Details
Main Authors: Kara, Ozgur, Chen, Yujia, Yang, Ming-Hsuan, Rehg, James M., Chu, Wen-Sheng, Tran, Du
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.20809
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917105238016000
author Kara, Ozgur
Chen, Yujia
Yang, Ming-Hsuan
Rehg, James M.
Chu, Wen-Sheng
Tran, Du
author_facet Kara, Ozgur
Chen, Yujia
Yang, Ming-Hsuan
Rehg, James M.
Chu, Wen-Sheng
Tran, Du
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2511_20809
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Layer-Aware Video Composition via Split-then-Merge
Kara, Ozgur
Chen, Yujia
Yang, Ming-Hsuan
Rehg, James M.
Chu, Wen-Sheng
Tran, Du
Computer Vision and Pattern Recognition
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
title Layer-Aware Video Composition via Split-then-Merge
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.20809