# Blended Point Cloud Diffusion for Localized Text-guided Shape Editing

arXiv: https://arxiv.org/abs/2507.15399 · HTML: https://mlsanity.com/paper/2507.15399/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 21 Jul 2025.

## Abstract (arXiv)

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.