Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing

About

While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a significant challenge due to the complexities of multi-view consistency and spatial control. Inspired by these 2D advancements, we present a novel personalization method for text-guided 3D editing that enables compositional, object-level control through natural language. Given a 3D input, we render orthogonal views and extract object-level segmentation masks to isolate semantic components. We then learn distinct token embeddings for each component through a tailored two-phase optimization strategy: multi-view textual inversion with attention alignment, followed by full fine-tuning of multi-view diffusion model. During inference, these disentangled tokens seamlessly compose with editing prompts to generate multi-view consistent images, which are subsequently lifted into high-fidelity textured 3D meshes. Extensive evaluations across diverse editing scenarios demonstrate that our method successfully transfers the flexibility of 2D personalization to 3D, achieving state-of-the-art edit faithfulness and identity preservation compared to existing baselines.

Jinxin Ai, Matthias Nie{\ss}ner, Ziya Erko\c{c}• 2026

Related benchmarks

TaskDatasetResultRank
3D EditingDreamEdit3D 25 editing cases
CLIPdir Score3.16
4
3D Object EditingDreamEdit3D Benchmark 25 editing cases 1.0 (test)
Prompt Alignment8.6
4
3D Object EditingUser Study 30 participants (test)
Prompt Alignment89.9
3
Showing 3 of 3 rows

Other info

Follow for update