Diffusion-Based Attention Warping for Consistent 3D Scene Editing

TL;DR

This paper introduces a diffusion-based method for 3D scene editing that maintains view consistency and realism by warping attention features across multiple perspectives using scene geometry, enabling high-fidelity scene manipulation.

Contribution

It presents a novel approach that uses attention feature warping with scene geometry to achieve consistent and realistic 3D scene edits, advancing current scene manipulation techniques.

Findings

Effective in generating versatile 3D scene edits

Maintains high view consistency and realism

Outperforms existing scene editing methods

Abstract

We present a novel method for 3D scene editing using diffusion models, designed to ensure view consistency and realism across perspectives. Our approach leverages attention features extracted from a single reference image to define the intended edits. These features are warped across multiple views by aligning them with scene geometry derived from Gaussian splatting depth estimates. Injecting these warped features into other viewpoints enables coherent propagation of edits, achieving high fidelity and spatial alignment in 3D space. Extensive evaluations demonstrate the effectiveness of our method in generating versatile edits of 3D scenes, significantly advancing the capabilities of scene manipulation compared to the existing methods. Project page: \url{https://attention-warp.github.io}