NeuSEditor: From Multi-View Images to Text-Guided Neural Surface Edits

TL;DR

NeuSEditor is a novel text-guided neural surface editing method that preserves scene identity and geometry, simplifies workflows, and outperforms existing techniques in quality and accuracy.

Contribution

It introduces an identity-preserving architecture and geometry-aware loss for improved editing of neural implicit surfaces from multi-view images.

Findings

Outperforms state-of-the-art methods like PDS and InstructNeRF2NeRF.

Enhances geometric and rendering quality significantly.

Simplifies editing workflow by removing need for dataset updates.

Abstract

Implicit surface representations are valued for their compactness and continuity, but they pose significant challenges for editing. Despite recent advancements, existing methods often fail to preserve identity and maintain geometric consistency during editing. To address these challenges, we present NeuSEditor, a novel method for text-guided editing of neural implicit surfaces derived from multi-view images. NeuSEditor introduces an identity-preserving architecture that efficiently separates scenes into foreground and background, enabling precise modifications without altering the scene-specific elements. Our geometry-aware distillation loss significantly enhances rendering and geometric quality. Our method simplifies the editing workflow by eliminating the need for continuous dataset updates and source prompting. NeuSEditor outperforms recent state-of-the-art methods like PDS and InstructNeRF2NeRF, delivering superior quantitative and qualitative results. For more visual results, visit: neuseditor.github.io.