Pro3D-Editor: A Progressive-Views Perspective for Consistent and Precise 3D Editing

Yang Zheng, Mengqi Huang, Nan Chen, Zhendong Mao

Keywords: 3D Edit, 3D Gaussian Splatting, multi-view diffusion model

TL;DR: We propose a novel progressive 3D editing framework to achieve consistent and precise 3D editing

Abstract: Text-guided 3D editing aims to precisely edit semantically relevant local 3D regions, which has significant potential for various practical applications ranging from 3D games to film production. Existing methods typically follow a view-indiscriminate paradigm: editing 2D views indiscriminately and projecting them back into 3D space. However, they overlook the different cross-view interdependencies, resulting in inconsistent multi-view editing. In this study, we argue that ideal consistent 3D editing can be achieved through a progressive-views paradigm, which propagates editing semantics from the editing-salient view to other editing-sparse views. Specifically, we propose Pro3D-Editor, a novel framework, which mainly includes Primary-view Sampler, Key-view Render, and Full-view Refiner. Primary-view Sampler dynamically samples and edits the most editing-salient view as the primary view. Key-view Render accurately propagates editing semantics from the primary view to other key views through its Mixture-of-View-Experts Low-Rank Adaption (MoVE-LoRA). Full-view Refiner edits and refines the 3D object based on the edited multi-views. Extensive experiments demonstrate that our method outperforms existing methods in editing accuracy and spatial consistency.

Primary Area: Applications (e.g., vision, language, speech and audio, Creative AI)

Submission Number: 1340