Catalyst4D: 通过动态传播实现高保真的3D到4D场景编辑
Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagation
AI总结：
本文提出Catalyst4D框架，通过动态传播实现高保真的4D场景编辑，保持时空一致性，优于现有方法。
摘要：
近期基于NeRF和3DGS的3D场景编辑技术实现了高质量静态场景编辑。然而，动态场景编辑仍具挑战性，因直接扩展2D扩散模型至4D常导致运动伪影、时间闪烁和不一致的风格传播。我们引入Catalyst4D框架，将高质量3D编辑转移到动态4D高斯场景中，保持空间和时间一致性。其核心是基于锚点的运动引导（AMG），从原始和编辑的高斯中构建结构稳定且空间代表性的锚点。这些锚点作为稳健的区域参考，通过最优传输建立对应关系，实现一致的变形传播，避免跨区域干扰或运动漂移。互补地，颜色不确定性引导的外观细化（CUAR）通过估计每个高斯的颜色不确定性，选择性地细化易受遮挡导致伪影的区域。大量实验表明，Catalyst4D实现了时间稳定、高保真的动态场景编辑，并在视觉质量和运动一致性方面优于现有方法。
英文摘要：
Recent advances in 3D scene editing using NeRF and 3DGS enable high-quality static scene editing. In contrast, dynamic scene editing remains challenging, as methods that directly extend 2D diffusion models to 4D often produce motion artifacts, temporal flickering, and inconsistent style propagation. We introduce Catalyst4D, a framework that transfers high-quality 3D edits to dynamic 4D Gaussian scenes while maintaining spatial and temporal coherence. At its core, Anchor-based Motion Guidance (AMG) builds a set of structurally stable and spatially representative anchors from both original and edited Gaussians. These anchors serve as robust region-level references, and their correspondences are established via optimal transport to enable consistent deformation propagation without cross-region interference or motion drift. Complementarily, Color Uncertainty-guided Appearance Refinement (CUAR) preserves temporal appearance consistency by estimating per-Gaussian color uncertainty and selectively refining regions prone to occlusion-induced artifacts. Extensive experiments demonstrate that Catalyst4D achieves temporally stable, high-fidelity dynamic scene editing and outperforms existing methods in both visual quality and motion coherence.
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。
