FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly

TL;DR

FocalDreamer is a novel framework for text-driven 3D editing that enables precise, separable, and region-specific modifications by assembling independent parts with high fidelity and style consistency.

Contribution

It introduces a new assembly-based approach with dual-path rendering and focal loss for fine-grained, controllable 3D editing guided by text prompts.

Findings

Superior editing capabilities demonstrated in experiments

High-fidelity geometry and PBR textures produced

Effective part-wise control and instance reuse achieved

Abstract

While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation. In response, we introduce FocalDreamer, a framework that merges base shape with editable parts according to text prompts for fine-grained editing within desired regions. Specifically, equipped with geometry union and dual-path rendering, FocalDreamer assembles independent 3D parts into a complete object, tailored for convenient instance reuse and part-wise control. We propose geometric focal loss and style consistency regularization, which encourage focal fusion and congruent overall appearance. Furthermore, FocalDreamer generates high-fidelity geometry and PBR textures which are compatible with widely-used graphics engines. Extensive experiments have highlighted the superior editing capabilities of FocalDreamer in both quantitative and qualitative evaluations.