发表机构
University of Delhi; Jadavpur University（德里大学; 贾达普大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出EditBench3D基准，从保真度、局部性、一致性和保持性四维度评估神经3D场景编辑，发现语义保真度与其他属性弱相关，且显式高斯编辑器整体平衡最佳。
AI 中文摘要
神经3D场景编辑通常仅通过语义对齐来评估，尽管一个令人信服的结果可能改变无关内容或在视图间变得不一致。我们引入了EditBench3D，一个与表示无关的基准，将编辑视为受控的信息替换。它评估四个互补的属性：指令保真度、空间局部性、跨视图一致性以及非目标内容的保持性。该协议结合了可见性感知的3D目标支持、配对描述、保留相机以及五个编辑族，涵盖外观、材质、几何和对象级变化。我们在240个场景-编辑对上评估了八个代表性的NeRF、3D高斯泼溅、混合和基于代理的编辑器。研究表明，语义保真度与其他编辑属性仅弱相关，并且没有单一方法在所有维度上最优。显式高斯编辑器提供了强大的整体平衡，而直接代理操作提供了最保守的编辑，但以开放保真度为代价。这些发现支持将可编辑性报告为多目标概况，而非单一语义分数。
英文摘要
Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent across views. We introduce EditBench3D, a representation-agnostic benchmark that treats editing as controlled information replacement. It evaluates four complementary properties: instruction fidelity, spatial locality, cross-view consistency, and preservation of non-target content. The protocol combines visibility-aware 3D target supports, paired descriptions, held-out cameras, and five edit families covering appearance, material, geometry, and object-level changes. We evaluate eight representative NeRF, 3D Gaussian Splatting, hybrid, and proxy-based editors on 240 scene-edit pairs. The study shows that semantic fidelity is only weakly associated with the other editing properties, and that no single method is optimal across all dimensions. Explicit Gaussian editors offer a strong overall balance, whereas direct proxy manipulation provides the most conservative edits at the cost of open-ended fidelity. These findings support reporting editability as a multi-objective profile rather than a single semantic score.
