Blended Point Cloud Diffusion for Localized Text-guided Shape Editing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sella, Etai, Atia, Noam, Mokady, Ron, Averbuch-Elor, Hadar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911067063451648
author Sella, Etai
Atia, Noam
Mokady, Ron
Averbuch-Elor, Hadar
author_facet Sella, Etai
Atia, Noam
Mokady, Ron
Averbuch-Elor, Hadar
contents Natural language offers a highly intuitive interface for enabling localized fine-grained edits of 3D shapes. However, prior works face challenges in preserving global coherence while locally modifying the input 3D shape. In this work, we introduce an inpainting-based framework for editing shapes represented as point clouds. Our approach leverages foundation 3D diffusion models for achieving localized shape edits, adding structural guidance in the form of a partial conditional shape, ensuring that other regions correctly preserve the shape's identity. Furthermore, to encourage identity preservation also within the local edited region, we propose an inference-time coordinate blending algorithm which balances reconstruction of the full shape with inpainting at a progression of noise levels during the inference process. Our coordinate blending algorithm seamlessly blends the original shape with its edited version, enabling a fine-grained editing of 3D shapes, all while circumventing the need for computationally expensive and often inaccurate inversion. Extensive experiments show that our method outperforms alternative techniques across a wide range of metrics that evaluate both fidelity to the original shape and also adherence to the textual description.
format Preprint
id arxiv_https___arxiv_org_abs_2507_15399
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Blended Point Cloud Diffusion for Localized Text-guided Shape Editing
Sella, Etai
Atia, Noam
Mokady, Ron
Averbuch-Elor, Hadar
Graphics
Computer Vision and Pattern Recognition
Natural language offers a highly intuitive interface for enabling localized fine-grained edits of 3D shapes. However, prior works face challenges in preserving global coherence while locally modifying the input 3D shape. In this work, we introduce an inpainting-based framework for editing shapes represented as point clouds. Our approach leverages foundation 3D diffusion models for achieving localized shape edits, adding structural guidance in the form of a partial conditional shape, ensuring that other regions correctly preserve the shape's identity. Furthermore, to encourage identity preservation also within the local edited region, we propose an inference-time coordinate blending algorithm which balances reconstruction of the full shape with inpainting at a progression of noise levels during the inference process. Our coordinate blending algorithm seamlessly blends the original shape with its edited version, enabling a fine-grained editing of 3D shapes, all while circumventing the need for computationally expensive and often inaccurate inversion. Extensive experiments show that our method outperforms alternative techniques across a wide range of metrics that evaluate both fidelity to the original shape and also adherence to the textual description.
title Blended Point Cloud Diffusion for Localized Text-guided Shape Editing
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.15399