视图至关重要：关键帧引导的文本驱动3D高斯编辑
View Matters: Keyframe-Guided Text-Driven 3D Gaussian Editing
浏览论文内容
中文总结 AI 辅助
提出View Matters框架，通过关键帧重要性估计和引导编辑，在3D高斯编辑中优先处理可靠视图，提升编辑质量与跨视图一致性。
中文摘要 AI 辅助
文本驱动的3D高斯编辑通常不区分渲染视图的编辑可靠性，尽管不同视点提供的监督质量差异显著。清晰展示场景并与编辑指令匹配的视图提供可靠的指导，而信息量较少的视图在所有视图被同等对待时可能会削弱编辑效果。我们提出View Matters，一种视图重要性感知框架，围绕可靠关键帧进行编辑。关键帧重要性估计（KIE）利用几何可见性、语义区分度和编辑相关性来识别可靠视图。关键帧引导编辑（KGE）随后将其编辑信号非对称地传播到非关键帧，避免噪声反向影响，而重要性感知优化（IAO）在3DGS优化过程中保持这种可靠性偏好。在23个场景-提示对中，View Matters在评估方法中实现了最高的平均CLIP文本-图像相似度0.2822和方向相似度0.2564，编辑时间为四分钟。额外的相邻视图分析表明，保真导向的编辑过程保持了跨视图一致性。
英文摘要
Text-driven 3D Gaussian editing commonly does not distinguish the editing reliability of rendered views, although different viewpoints provide supervision of substantially different quality. Views that clearly show the scene and match the edit instruction provide reliable guidance, while less informative views may weaken the edit when all views are treated equally. We present View Matters, a view-importance-aware framework that conducts editing around reliable keyframes. Keyframe Importance Estimation (KIE) identifies reliable views using geometric visibility, semantic distinctiveness, and edit relevance. Keyframe-Guided Editing (KGE) then propagates their editing signals asymmetrically to non-keyframes without noisy reverse influence, while Importance-Aware Optimization (IAO) preserves this reliability preference during 3DGS optimization. Across 23 scene-prompt pairs, View Matters achieves the highest average CLIP text-image similarity of 0.2822 and directional similarity of 0.2564 among the evaluated methods, with a four-minute editing time. Additional adjacent-view analysis indicates that the fidelity-oriented editing process maintains cross-view coherence.
