Blended Point Cloud Diffusion for Localized Text-guided Shape Editing

• URL: http://arxiv.org/abs/2507.15399v1
• Date: Mon, 21 Jul 2025 09:00:19 GMT
• Title: Blended Point Cloud Diffusion for Localized Text-guided Shape Editing
• Authors: Etai Sella, Noam Atia, Ron Mokady, Hadar Averbuch-Elor,
• Abstract summary: In this work, we introduce an inpainting-based framework for editing shapes represented as point clouds.<n>We propose an inference-time coordinate blending algorithm which balances reconstruction of the full shape with inpainting.<n>Our coordinate blending algorithm seamlessly blends the original shape with its edited version, enabling a fine-grained editing of 3D shapes.
• Score: 12.332668298895717
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform [62.27337227010514]
  We introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with Local Shape Transform, dubbed RIST. RIST learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. RIST demonstrates state-of-the-art performances on 3D part label transfer and semantic keypoint transfer given arbitrarily rotated point cloud pairs.
  arXiv  Detail & Related papers  (2024-04-17T08:09:25Z)
• ShapeFusion: A 3D diffusion model for localized shape editing [37.82690898932135]
  We propose an effective diffusion masking training strategy that, by design, facilitates localized manipulation of any shape region. Compared to the current state-of-the-art our method leads to more interpretable shape manipulations than methods relying on latent code state.
  arXiv  Detail & Related papers  (2024-03-28T18:50:19Z)
• NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation [52.772319840580074]
  3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints. Existing methods often decompose 3D shapes into a sequence of localized components, treating each element in isolation. We introduce a novel spatial-aware 3D shape generation framework that leverages 2D plane representations for enhanced 3D shape modeling.
  arXiv  Detail & Related papers  (2024-03-27T04:09:34Z)
• CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization [56.47175002368553]
  This paper introduces a new approach based on a coupled representation and a neural volume optimization to implicitly perform 3D shape editing in latent space. First, we design the coupled neural shape representation for supporting 3D shape editing. Second, we formulate the coupled neural shape optimization procedure to co-optimize the two coupled components in the representation subject to the editing operation.
  arXiv  Detail & Related papers  (2024-02-04T01:52:56Z)
• EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation [124.27302003578903]
  This paper presents a new text-guided technique for generating 3D shapes. We leverage a hybrid 3D representation, namely EXIM, combining the strengths of explicit and implicit representations. We demonstrate the applicability of our approach to generate indoor scenes with consistent styles using text-induced 3D shapes.
  arXiv  Detail & Related papers  (2023-11-03T05:01:51Z)
• DragD3D: Realistic Mesh Editing with Rigidity Control Driven by 2D Diffusion Priors [10.355568895429588]
  Direct mesh editing and deformation are key components in the geometric modeling and animation pipeline. Regularizers are not aware of the global context and semantics of the object. We show that our deformations can be controlled to yield realistic shape deformations aware of the global context.
  arXiv  Detail & Related papers  (2023-10-06T19:55:40Z)
• Geometrically Consistent Partial Shape Matching [50.29468769172704]
  Finding correspondences between 3D shapes is a crucial problem in computer vision and graphics. An often neglected but essential property of matching geometrics is consistency. We propose a novel integer linear programming partial shape matching formulation.
  arXiv  Detail & Related papers  (2023-09-10T12:21:42Z)
• Learning to generate shape from global-local spectra [0.0]
  We build our method on top of recent advances on the so called shape-from-spectrum paradigm. We consider the spectrum as a natural and ready to use representation to encode variability of the shapes. Our results confirm the improvement of the proposed approach in comparison to existing and alternative methods.
  arXiv  Detail & Related papers  (2021-08-04T16:39:56Z)
• Unsupervised Learning of Intrinsic Structural Representation Points [50.92621061405056]
  Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points.
  arXiv  Detail & Related papers  (2020-03-03T17:40:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.