PrEditor3D: Fast and Precise 3D Shape Editing
Abstract
We propose a training-free approach to 3D editing that enables the editing of a single shape and the reconstruction of a mesh within a few minutes. Leveraging 4-view images, user-guided text prompts, and rough 2D masks, our method produces an edited 3D mesh that aligns with the prompt. For this, our approach performs synchronized multi-view image editing in 2D. However, targeted regions to be edited are ambiguous due to projection from 3D to 2D. To ensure precise editing only in intended regions, we develop a 3D segmentation pipeline that detects edited areas in 3D space. Additionally, we introduce a merging algorithm to seamlessly integrate edited 3D regions with original input. Extensive experiments demonstrate the superiority of our method over previous approaches, enabling fast, high-quality editing while preserving unintended regions.
Cite
Text
Erkoç et al. "PrEditor3D: Fast and Precise 3D Shape Editing." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00068Markdown
[Erkoç et al. "PrEditor3D: Fast and Precise 3D Shape Editing." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/erkoc2025cvpr-preditor3d/) doi:10.1109/CVPR52734.2025.00068BibTeX
@inproceedings{erkoc2025cvpr-preditor3d,
title = {{PrEditor3D: Fast and Precise 3D Shape Editing}},
author = {Erkoç, Ziya and Gümeli, Can and Wang, Chaoyang and Nießner, Matthias and Dai, Angela and Wonka, Peter and Lee, Hsin-Ying and Zhuang, Peiye},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2025},
pages = {640-649},
doi = {10.1109/CVPR52734.2025.00068},
url = {https://mlanthology.org/cvpr/2025/erkoc2025cvpr-preditor3d/}
}