We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs into editable 3D entities (layering), (ii) editing them in Blender with 3D-grounded control (editing), and (iii) fusing them into a coherent scene using a generative compositor (compositing). Our generative compositor extends a pre-trained diffusion model to process both the original (source) and edited (target) scenes in parallel. It is fine-tuned on video frames with two key training strategies: (i) source masking, enabling flexible modifications like background replacement; (ii) simulated object jittering, facilitating disentangled control over objects and camera. BlenderFusion significantly outperforms prior methods in complex compositional scene editing tasks.
@article{arxiv.2506.17450,
title = {BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing},
author = {Jiacheng Chen and Ramin Mehran and Xuhui Jia and Saining Xie and Sanghyun Woo},
journal= {arXiv preprint arXiv:2506.17450},
year = {2025}
}