TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts

TL;DR

TIP-Editor is a novel 3D scene editing framework that integrates text and image prompts with bounding boxes, enabling precise control over appearance and location of edits, outperforming existing methods in accuracy and quality.

Contribution

The paper introduces TIP-Editor, a new 3D editing approach that combines text and image prompts with bounding boxes and uses 3D Gaussian splatting for precise local edits.

Findings

Achieves accurate 3D editing aligned with prompts and bounding boxes

Outperforms baselines in editing quality and prompt alignment

Utilizes a stepwise 2D personalization strategy and localization loss

Abstract

Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the inherent limitations of the text description. To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region. With the image prompt, users can conveniently specify the detailed appearance/style of the target content in complement to the text description, enabling accurate control of the appearance. Specifically, TIP-Editor employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image, in which a localization loss is proposed to encourage correct object placement as specified by the bounding box. Additionally, TIPEditor utilizes explicit and flexible 3D Gaussian splatting as the 3D representation to facilitate local editing while keeping the background unchanged. Extensive experiments have demonstrated that TIP-Editor conducts accurate editing following the text and image prompts in the specified bounding box region, consistently outperforming the baselines in editing quality, and the alignment to the prompts, qualitatively and quantitatively.