SPLICE: Part-Level 3D Shape Editing from Local Semantic Extraction to Global Neural Mixing

TL;DR

SPLICE introduces a part-level neural implicit representation for 3D shapes that allows intuitive, structure-aware editing operations like translation, rotation, and part mixing, improving flexibility and fidelity in shape manipulation.

Contribution

The paper proposes a novel part-level neural implicit model with independent part encoding and a global attention decoder for high-fidelity, structure-aware 3D shape editing.

Findings

Outperforms existing methods in qualitative shape editing tasks

Enables flexible part-level transformations and mixing

Maintains semantic consistency and structural plausibility

Abstract

Neural implicit representations of 3D shapes have shown great potential in 3D shape editing due to their ability to model high-level semantics and continuous geometric representations. However, existing methods often suffer from limited editability, lack of part-level control, and unnatural results when modifying or rearranging shape parts. In this work, we present SPLICE, a novel part-level neural implicit representation of 3D shapes that enables intuitive, structure-aware, and high-fidelity shape editing. By encoding each shape part independently and positioning them using parameterized Gaussian ellipsoids, SPLICE effectively isolates part-specific features while discarding global context that may hinder flexible manipulation. A global attention-based decoder is then employed to integrate parts coherently, further enhanced by an attention-guiding filtering mechanism that prevents information leakage across symmetric or adjacent components. Through this architecture, SPLICE supports various part-level editing operations, including translation, rotation, scaling, deletion, duplication, and cross-shape part mixing. These operations enable users to flexibly explore design variations while preserving semantic consistency and maintaining structural plausibility. Extensive experiments demonstrate that SPLICE outperforms existing approaches both qualitatively and quantitatively across a diverse set of shape-editing tasks.