Adaptive Scaling with Geometric and Visual Continuity of completed 3D objects

TL;DR

This paper presents a novel framework that enables flexible, structurally coherent scaling of completed 3D objects represented by Signed Distance Fields, overcoming the rigidity of traditional object completion methods.

Contribution

The authors introduce a part-aware scaling method that transforms static SDFs into editable, deformable objects with preserved geometric and visual continuity, including a repetition-based strategy for large deformations.

Findings

Enables artifact-free, proportional deformation of completed 3D objects.

Outperforms naive scaling methods in visual quality and structural preservation.

Effective on complex shapes and repetitive structures in real-world datasets.

Abstract

Object completion networks typically produce static Signed Distance Fields (SDFs) that faithfully reconstruct geometry but cannot be rescaled or deformed without introducing structural distortions. This limitation restricts their use in applications requiring flexible object manipulation, such as indoor redesign, simulation, and digital content creation. We introduce a part-aware scaling framework that transforms these static completed SDFs into editable, structurally coherent objects. Starting from SDFs and Texture Fields generated by state-of-the-art completion models, our method performs automatic part segmentation, defines user-controlled scaling zones, and applies smooth interpolation of SDFs, color, and part indices to enable proportional and artifact-free deformation. We further incorporate a repetition-based strategy to handle large-scale deformations while preserving repeating geometric patterns. Experiments on Matterport3D and ShapeNet objects show that our method overcomes the inherent rigidity of completed SDFs and is visually more appealing than global and naive selective scaling, particularly for complex shapes and repetitive structures.