通过渐进式编辑解决3D场景生成不一致问题，效果媲美复杂模型。
ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing
- 将大任务拆解为多个子任务，逐步推进以减少多视角差异。
- 在多个场景和挑战性任务中达到顶级效果，无需复杂附加模块。
- 支持实时调控编辑强度，适合需要精细控制的用户。
本文提出ProEdit——一种基于扩散蒸馏的简单而有效的高质3D场景编辑框架，采用新颖的渐进式策略。受观察启发：场景编辑中的多视图不一致性源于扩散模型庞大的可行输出空间（FOS），本框架通过控制FOS大小并分解整体编辑任务为若干子任务，逐个在场景上执行。设计了难度感知的子任务调度器与自适应3D高斯点云（3DGS）训练策略，确保每个子任务高效高质量完成。大量实验表明，ProEdit在多种场景及挑战性编辑任务中均达当前最优性能，且仅依赖简单框架，无需昂贵或复杂的附加组件如蒸馏损失、额外模块或训练流程。特别地，ProEdit还提供了在编辑过程中动态控制、预览与选择编辑‘激进程度’的新方式。
原文摘要 · Abstract (English)
This paper proposes ProEdit - a simple yet effective framework for high-quality 3D scene editing guided by diffusion distillation in a novel progressive manner. Inspired by the crucial observation that multi-view inconsistency in scene editing is rooted in the diffusion model's large feasible output space (FOS), our framework controls the size of FOS and reduces inconsistency by decomposing the overall editing task into several subtasks, which are then executed progressively on the scene. Within this framework, we design a difficulty-aware subtask decomposition scheduler and an adaptive 3D Gaussian splatting (3DGS) training strategy, ensuring high quality and efficiency in performing each subtask. Extensive evaluation shows that our ProEdit achieves state-of-the-art results in various scenes and challenging editing tasks, all through a simple framework without any expensive or sophisticated add-ons like distillation losses, components, or training procedures. Notably, ProEdit also provides a new way to control, preview, and select the "aggressivity" of editing operation during the editing process.
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。