Interp3D: Correspondence-aware Interpolation for Generative Textured 3D Morphing

2026-01-20

AI Summary

Existing 3D deformation methods often struggle to simultaneously preserve geometric consistency and texture detail, frequently resulting in semantic ambiguity, structural misalignment, and texture distortion. This work proposes a training-free 3D textured deformation framework that, for the first time, jointly optimizes geometry and texture alignment without requiring any training. By integrating conditional spatial semantic alignment, SLAT (Structured Latent)-guided structural interpolation, and fine-grained texture fusion, the method achieves smooth transitions that maintain both appearance fidelity and geometric coherence. Extensive experiments on our newly curated Interp3DData dataset demonstrate that the proposed approach significantly outperforms state-of-the-art methods in terms of fidelity, smoothness, and plausibility, with both quantitative metrics and human evaluations confirming its effectiveness.

Technology Category

• Computer Vision: 3D Computer Vision
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Learning with Manifolds

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Textured 3D morphing seeks to generate smooth and plausible transitions between two 3D assets, preserving both structural coherence and fine-grained appearance. This ability is crucial not only for advancing 3D generation research but also for practical applications in animation, editing, and digital content creation. Existing approaches either operate directly on geometry, limiting them to shape-only morphing while neglecting textures, or extend 2D interpolation strategies into 3D, which often causes semantic ambiguity, structural misalignment, and texture blurring. These challenges underscore the necessity to jointly preserve geometric consistency, texture alignment, and robustness throughout the transition process. To address this, we propose Interp3D, a novel training-free framework for textured 3D morphing. It harnesses generative priors and adopts a progressive alignment principle to ensure both geometric fidelity and texture coherence. Starting from semantically aligned interpolation in condition space, Interp3D enforces structural consistency via SLAT (Structured Latent)-guided structure interpolation, and finally transfers appearance details through fine-grained texture fusion. For comprehensive evaluations, we construct a dedicated dataset, Interp3DData, with graded difficulty levels and assess generation results from fidelity, transition smoothness, and plausibility. Both quantitative metrics and human studies demonstrate the significant advantages of our proposed approach over previous methods. Source code is available at https://github.com/xiaolul2/Interp3D.

Problem

• textured 3D morphing
• geometric consistency
• texture alignment
• semantic ambiguity
• structural misalignment

Innovation

• textured 3D morphing
• correspondence-aware interpolation
• generative priors
• structured latent alignment
• progressive alignment