BlenderFusion：基于3D锚定的视觉编辑与生成式合成
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing
AI总结：
研究提出BlenderFusion生成式视觉合成框架，通过分层-编辑-合成流水线，结合扩展预训练扩散模型的生成合成器与两项训练策略，实现3D锚定的场景编辑，性能显著优于现有方法。
摘要：
我们提出BlenderFusion，这是一种生成式视觉合成框架，通过重组对象、相机和背景来合成新场景。它遵循“分层-编辑-合成”流水线：（i）将视觉输入分割并转换为可编辑的3D实体（分层）；（ii）在Blender中通过基于3D锚定的控制对其进行编辑（编辑）；（iii）使用生成合成器将它们融合为连贯场景（合成）。我们的生成合成器扩展了预训练扩散模型，可并行处理原始（源）场景和编辑后（目标）场景。它在视频帧上微调，采用两项关键训练策略：（i）源掩码，支持背景替换等灵活修改；（ii）模拟对象抖动，实现对对象和相机的解耦控制。BlenderFusion在复杂合成场景编辑任务中显著优于现有方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
