InstructMix2Mix：通过多视图模型个性化实现一致的稀疏视图编辑
InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalization
将多视图扩散模型作为SDS中的学生模型，替代神经场整合器，并引入增量更新、教师噪声调度和注意力修改，为稀疏视图编辑提供可复用的跨视图一致性蒸馏框架。
原文依据 replacing the conventional neural field consolidator in Score Distillation Sampling (SDS) with a multi-view diffusion student
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们研究稀疏输入视图下的多视图图像编辑任务，其中输入可视为从不同视角捕获场景的图像混合。目标是根据文本指令修改场景，同时保持所有视图间的一致性。现有基于逐场景神经场或时序注意力机制的方法在此设定下表现不佳，常产生伪影和不连贯的编辑。我们提出InstructMix2Mix（I-Mix2Mix）框架，将2D扩散模型的编辑能力蒸馏到预训练的多视图扩散模型中，利用其数据驱动的3D先验实现跨视图一致性。一个关键贡献是用多视图扩散学生模型替换分数蒸馏采样（SDS）中传统的神经场整合器，这需要新颖的适配：跨时间步的增量学生更新、防止退化的专用教师噪声调度器，以及在不增加额外成本的情况下增强跨视图连贯性的注意力修改。实验表明，I-Mix2Mix在保持高单帧编辑质量的同时显著提升了多视图一致性。
英文原文摘要 1179 字符
We address the task of multi-view image editing from sparse input views, where the inputs can be seen as a mix of images capturing the scene from different viewpoints. The goal is to modify the scene according to a textual instruction while preserving consistency across all views. Existing methods, based on per-scene neural fields or temporal attention mechanisms, struggle in this setting, often producing artifacts and incoherent edits. We propose InstructMix2Mix (I-Mix2Mix), a framework that distills the editing capabilities of a 2D diffusion model into a pretrained multi-view diffusion model, leveraging its data-driven 3D prior for cross-view consistency. A key contribution is replacing the conventional neural field consolidator in Score Distillation Sampling (SDS) with a multi-view diffusion student, which requires novel adaptations: incremental student updates across timesteps, a specialized teacher noise scheduler to prevent degeneration, and an attention modification that enhances cross-view coherence without additional cost. Experiments demonstrate that I-Mix2Mix significantly improves multi-view consistency while maintaining high per-frame edit quality.