View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity

TL;DR

This paper introduces a novel framework for text-driven 3D scene editing that explicitly models cross-view dependencies, ensuring view consistency through dual-path structural and semantic mechanisms, and demonstrates superior performance on a new dataset.

Contribution

It proposes a view-consistent 3D editing method with dual-path structural and semantic cues, addressing cross-view inconsistency more robustly than prior approaches.

Findings

Achieves superior editing performance with consistent multi-view outputs.

Introduces a paired multi-view editing dataset for training and evaluation.

Demonstrates robustness and generalization in complex scene editing.

Abstract

Text-driven 3D scene editing has recently attracted increasing attention. Most existing methods follow a render-edit-optimize pipeline, where multi-view images are rendered from a 3D scene, edited with 2D image editors, and then used to optimize the underlying 3D representation. However, cross-view inconsistency remains a major bottleneck. Although recent methods introduce geometric cues, cross-view interactions, or video priors to mitigate this issue, they still largely rely on inference-time synchronization and thus remain limited in robustness and generalization.In this work, we recast multi-view consistent 3D editing from a distributional perspective: 3D scene editing essentially requires a joint distribution modeling across viewpoints.Based on this insight, we propose a view-consistent 3D editing framework that explicitly introduces cross-view dependencies into the editing process. Furthermore, motivated by the observation that structural correspondence and semantic continuity rely on different cross-view cues, we introduce a dual-path consistency mechanism consisting of projection-guided structural guidance and patch-level semantic propagation for effective cross-view editing. Further, we construct a paired multi-view editing dataset that provides reliable supervision for learning cross-view consistency in edited scenes. Extensive experiments demonstrate that our method achieves superior editing performance with precise and consistent views for complex scenes.