What question did this study set out to answer?

The aim is to develop a method for editing 3D scenes using text prompts without needing to retrain models for different edits.

Editing 3D Scenes via Text Prompts without Retraining

View Full Paper

Ask AI

Bookmark

The aim is to develop a method for editing 3D scenes using text prompts without needing to retrain models for different edits.
Proposes a text-driven 3D scene editing method called DN2N.
Utilizes existing text-based editing models from 2D images.
Introduces content filtering to improve 3D consistency.
Develops a new NeRF model structure and cross-view regularization terms.
Achieves multiple types of edits such as appearance changes and weather transitions.
Eliminates the need to retrain models for specific scenes or edits.
Demonstrates comparable editing time to existing methods, enhancing practical value.

No takes yet. Share an insight, caveat, or question.

Novel text-driven method enhances 3D scene editing capabilities, suggesting efficiency and versatility in applications.

Fang et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark