CVNov 7, 2024

ProEdit: Simple Progression is All You Need for High-Quality 3D Scene Editing

arXiv:2411.05006v114 citationsh-index: 6NIPS
Originality Incremental advance
AI Analysis

This addresses high-quality 3D scene editing for applications like virtual reality or content creation, but it appears incremental as it builds on existing diffusion and 3D Gaussian splatting methods.

The paper tackles the problem of multi-view inconsistency in 3D scene editing by proposing ProEdit, a framework that decomposes editing into progressive subtasks to control the diffusion model's output space, achieving state-of-the-art results in various scenes and editing tasks without expensive add-ons.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes