Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) remains challenging due to inadequate 4D scene understanding and a lack of proper optical interactions, such as shadows and reflections. To address these limitations, we present InsertAnywhere, a comprehensive VOI framework that achieves geometrically grounded object placement and optics-aware video synthesis. Our approach first leverages a 4D-aware mask generation module that allows users to anchor an object's 3D pose in a single frame. The framework automatically propagates this placement across the video, accurately handling local scene dynamics and occlusions. To synthesize realistic physical lighting interactions, we introduce Optics-Aware Representation Alignment, a novel strategy that utilizes an extended mask to guide feature extraction, enabling optical effects to seamlessly extend beyond the inserted object's boundary. Finally, to overcome the lack of training data for such phenomena, we construct and open-source ROSE++, a specialized quadruplet dataset tailored for the supervised learning of optical effects. Extensive experiments demonstrate that InsertAnywhere produces geometrically plausible and photometrically realistic insertions in complex real-world scenarios, significantly outperforming existing research and commercial generative tools.
On VOIBench (200 clips), our method outperforms both commercial and open-source baselines on nearly every metric.
Sequentially adding our components progressively improves occlusion handling, object fidelity, and optics-aware generation.
Each component contributes, with the align loss giving the largest gain in imaging quality.
@misc{jin2026insertanywheregeometricallygroundedopticsaware,
title={InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion},
author={Hoiyeong Jin and Hyojin Jang and Junha Hyung and Jeongho Kim and Kinam Kim and Dongjin Kim and Huijin Choi and Hyeonji Kim and Jaegul Choo},
year={2026},
eprint={2512.17504},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2512.17504},
}