TRACE：通过可触觉重建和几何对齐的上下文视频遮罩实现高保真的3D场景编辑
TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking
AI总结：
TRACE通过可触觉重建和几何对齐的上下文视频遮罩，实现高保真的3D场景编辑，解决了现有方法在局部姿态调整和组件替换时结构完整性不足的问题。
摘要：
我们提出了TRACE，一种基于网格的3DGS编辑框架，实现了自动且高保真的场景变换。通过将视频扩散与显式的3D几何结构相结合，TRACE能够实现细粒度的部分级操作，如局部姿态调整或组件替换，同时保持主体结构的完整性。我们的方法包含三个关键阶段：(1) 多视角3D-锚点合成，利用在我们的MV-TRACE数据集上训练的稀疏视角编辑器生成空间一致的3D-锚点；(2) 可触觉几何锚定（TGA），通过两阶段注册确保插入的网格与3DGS场景的空间同步；(3) 上下文视频遮罩（CVM），将3D投影整合到自回归视频管道中，实现时间稳定且物理基础的渲染。广泛的实验表明，TRACE在编辑多样性和结构完整性方面均优于现有方法。
英文摘要：
Existing 3D Gaussian Splatting (3DGS) editing methods primarily focus on appearance modification and often struggle to support flexible geometry editing while preserving structural integrity and scene-consistent appearance. To address this limitation, we present TRACE, a mesh-guided 3DGS editing framework that automatically aligns explicit 3D geometry with Gaussian scenes and decouples Geometric Anchoring from Appearance Harmonization. First, Multi-view 3D-Anchor Synthesis, trained on our MV-TRACE dataset for scene-coherent object addition and modification, generates geometrically aligned editing anchors, while Tangible Geometry Alignment (TGA) performs coarse-to-fine mesh-scene registration. Then, Contextual Video Masking (CVM) integrates projected 3D anchors into an autoregressive video diffusion pipeline, harmonizing their appearance with the surrounding scene while maintaining multi-view consistency. We evaluate TRACE on eight held-out scenes across six editing categories. TRACE completes each edit in approximately 10 minutes on a single NVIDIA RTX Pro 6000 GPU. Extensive experiments demonstrate consistent improvements over existing methods in editing versatility, structural integrity, semantic alignment, multi-view consistency, and visual quality.
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。
