通过分离静态与动态信息，实现高效4D场景编辑。
Instruct-4DGS: Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
- 用4D高斯表示法分离静态3D高斯与动态形变场。
- 仅编辑静态部分，使处理时间减半且效果更贴合指令。
- 引入评分蒸馏机制修复编辑后错位问题，适合交互式编辑场景。
现有4D动态场景编辑方法需处理数千张2D图像并进行额外训练循环，单次编辑耗时数小时，难以扩展至长时序场景。本文提出Instruct-4DGS，一种更适用于时间维度的高效动态场景编辑方法。该方法采用4D高斯表示，将4D动态场景建模为静态3D高斯与基于Hexplane的形变场的组合，仅对静态3D高斯进行编辑，这是视觉编辑所需的最小且充分组件。为解决编辑后静态高斯与形变场之间的错位问题，引入基于评分蒸馏的优化阶段。大量实验表明，Instruct-4DGS显著提升效率，编辑时间减少超过50%，同时生成更符合用户指令的高质量结果。
原文摘要 · Abstract (English)
Recent 4D dynamic scene editing methods require editing thousands of 2D images used for dynamic scene synthesis and updating the entire scene with additional training loops, resulting in several hours of processing to edit a single dynamic scene. Therefore, these methods are not scalable with respect to the temporal dimension of the dynamic scene (i.e., the number of timesteps). In this work, we propose Instruct-4DGS, an efficient dynamic scene editing method that is more scalable in terms of temporal dimension. To achieve computational efficiency, we leverage a 4D Gaussian representation that models a 4D dynamic scene by combining static 3D Gaussians with a Hexplane-based deformation field, which captures dynamic information. We then perform editing solely on the static 3D Gaussians, which is the minimal but sufficient component required for visual editing. To resolve the misalignment between the edited 3D Gaussians and the deformation field, which may arise from the editing process, we introduce a refinement stage using a score distillation mechanism. Extensive editing results demonstrate that Instruct-4DGS is efficient, reducing editing time by more than half compared to existing methods while achieving high-quality edits that better follow user instructions. Code and results: https://hanbyelcho.info/instruct-4dgs/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。