DM-CFO: A Diffusion Model for Compositional 3D Tooth Generation with Collision-Free Optimization

2026-03-03

AI Summary

This work addresses the challenge of generating 3D dental structures that simultaneously achieve global coherence and geometric collision-free configurations. The authors propose a novel framework integrating diffusion models with 3D Gaussian representations, where text and graph-structured constraints are incorporated during the denoising process to guide the placement of missing teeth. The method employs score distillation sampling to alternately optimize Gaussian parameters for both teeth and jawbones, while explicitly enforcing geometric feasibility through a collision-aware regularizer based on inter-tooth distances. This approach is the first to combine diffusion-based generation with collision-aware optimization, enabling the synthesis of anatomically plausible, self-collision-free, and multi-view consistent composite 3D dental models. Extensive experiments on three real-world datasets demonstrate significant improvements in both visual quality and anatomical realism over existing methods.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

The automatic design of a 3D tooth model plays a crucial role in dental digitization. However, current approaches face challenges in compositional 3D tooth generation because both the layouts and shapes of missing teeth need to be optimized.In addition, collision conflicts are often omitted in 3D Gaussian-based compositional 3D generation, where objects may intersect with each other due to the absence of explicit geometric information on the object surfaces. Motivated by graph generation through diffusion models and collision detection using 3D Gaussians, we propose an approach named DM-CFO for compositional tooth generation, where the layout of missing teeth is progressively restored during the denoising phase under both text and graph constraints. Then, the Gaussian parameters of each layout-guided tooth and the entire jaw are alternately updated using score distillation sampling (SDS). Furthermore, a regularization term based on the distances between the 3D Gaussians of neighboring teeth and the anchor tooth is introduced to penalize tooth intersections. Experimental results on three tooth-design datasets demonstrate that our approach significantly improves the multiview consistency and realism of the generated teeth compared with existing methods. Project page: https://amateurc.github.io/CF-3DTeeth/.

Problem

• compositional 3D tooth generation
• collision-free optimization
• 3D Gaussian representation
• tooth layout
• shape realism

Innovation

• Diffusion Model
• Compositional 3D Generation
• Collision-Free Optimization
• 3D Gaussians
• Score Distillation Sampling