Over++: Generative Video Compositing for Layer Interaction Effects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qi, Luchao, Wu, Jiaye, Choi, Jun Myeong, Phillips, Cary, Sengupta, Roni, Goldman, Dan B
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914214922158080
author Qi, Luchao
Wu, Jiaye
Choi, Jun Myeong
Phillips, Cary
Sengupta, Roni
Goldman, Dan B
author_facet Qi, Luchao
Wu, Jiaye
Choi, Jun Myeong
Phillips, Cary
Sengupta, Roni
Goldman, Dan B
contents In professional video compositing workflows, artists must manually create environmental interactions-such as shadows, reflections, dust, and splashes-between foreground subjects and background layers. Existing video generative models struggle to preserve the input video while adding such effects, and current video inpainting methods either require costly per-frame masks or yield implausible results. We introduce augmented compositing, a new task that synthesizes realistic, semi-transparent environmental effects conditioned on text prompts and input video layers, while preserving the original scene. To address this task, we present Over++, a video effect generation framework that makes no assumptions about camera pose, scene stationarity, or depth supervision. We construct a paired effect dataset tailored for this task and introduce an unpaired augmentation strategy that preserves text-driven editability. Our method also supports optional mask control and keyframe guidance without requiring dense annotations. Despite training on limited data, Over++ produces diverse and realistic environmental effects and outperforms existing baselines in both effect generation and scene preservation.
format Preprint
id arxiv_https___arxiv_org_abs_2512_19661
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Over++: Generative Video Compositing for Layer Interaction Effects
Qi, Luchao
Wu, Jiaye
Choi, Jun Myeong
Phillips, Cary
Sengupta, Roni
Goldman, Dan B
Computer Vision and Pattern Recognition
In professional video compositing workflows, artists must manually create environmental interactions-such as shadows, reflections, dust, and splashes-between foreground subjects and background layers. Existing video generative models struggle to preserve the input video while adding such effects, and current video inpainting methods either require costly per-frame masks or yield implausible results. We introduce augmented compositing, a new task that synthesizes realistic, semi-transparent environmental effects conditioned on text prompts and input video layers, while preserving the original scene. To address this task, we present Over++, a video effect generation framework that makes no assumptions about camera pose, scene stationarity, or depth supervision. We construct a paired effect dataset tailored for this task and introduce an unpaired augmentation strategy that preserves text-driven editability. Our method also supports optional mask control and keyframe guidance without requiring dense annotations. Despite training on limited data, Over++ produces diverse and realistic environmental effects and outperforms existing baselines in both effect generation and scene preservation.
title Over++: Generative Video Compositing for Layer Interaction Effects
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.19661