Deep Spectral Models for Robust Dental Shape Generation

• URL: http://arxiv.org/abs/2606.31293v1
• Date: Tue, 30 Jun 2026 08:10:05 GMT
• Title: Deep Spectral Models for Robust Dental Shape Generation
• Abstract summary: ToothForge is a deep spectral generative framework that models dental crown geometries from compact, intrinsic representations.<n>By operating in the spectral domain, ToothForge learns a latent manifold of 3D tooth shapes through synchronized spectral embeddings.<n>Results show that ToothForge achieves reconstruction and generative performance comparable to or exceeding spatial approaches.
• Score: 0.22399170518036912
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate modeling of dental crown morphology is fundamental for diagnosis, orthodontic planning, and computer-aided restoration design. However, datasets suitable for training such models are typically limited in size. We present ToothForge, a deep spectral generative framework that models dental crown geometries from compact, intrinsic representations. By operating in the spectral domain, ToothForge learns a latent manifold of 3D tooth shapes through synchronized spectral embeddings, ensuring consistent modeling across samples with varying connectivity. Spectral synchronization mitigates the instability of Laplace-Beltrami eigenbases and enables efficient learning in a low-dimensional space. The framework is thoroughly evaluated through robustness analysis, ablation studies, and benchmarking against PCA-based statistical shape models and point-based generative frameworks. Results show that synchronized spectral modeling achieves reconstruction and generative performance comparable to or exceeding spatial approaches, while maintaining compactness and geometric interpretability. Together, the compact synchronized coefficients and low-dimensional learning space make the framework particularly suitable for limited datasets, as often encountered in dental and medical domains, and applicable in real-world scenarios where guaranteeing consistent connectivity across shapes from various clinics is unrealistic.

Related papers

• B-Spline Embedded Structure Learning for 3D Tooth Segmentation [4.713922533924589]
  Bline Embedded Structure Learning is a novel framework that distills the inherent sequential arrangement of teeth into a continuous structural constraint.<n>Our method establishes a new state-of-the-art accuracy with exceptional structural robustness and efficiency in computational overhead.
  arXiv  Detail & Related papers  (2026-08-18T02:43:49Z)
• Learning Spatio-Temporal Foundation Models from Pure Synthetic Data [85.23980441738811]
  NeoST is a scalable synthetic-training corpus to real-world bias, a latent-space reasoning architecture that generates and iteratively refines multiple future trajectories, and latent-space objectives that emphasize structural dynamics and enable inference-time correction under distribution shifts.<n>Extensive experiments across diverse real-world benchmarks show that NeoST consistently outperforms existing STFMs in diverse real-worldtemporal systems.
  arXiv  Detail & Related papers  (2026-06-27T02:56:46Z)
• Geometry-Aware Dataset Condensation for Diffusion Model Training [103.45641113998839]
  We propose to reformulate real subset selection as a geometry-aware distribution alignment problem.<n>By incorporating one-sided partial optimal transport, our method selectively aligns a compact subset with the full data distribution.<n>Experiments across diffusion variants, subset sizes, image resolutions, and training rounds show that our method achieves superior fidelity and distributional coverage.
  arXiv  Detail & Related papers  (2026-06-04T08:53:58Z)
• PathAR: Structure-First Autoregressive Synthesis of Multimodal Pathology Images [51.428093790826814]
  We propose pathology Autorgressive modeling (PathAR) to factorize structure and appearance for modality-label-conditioned pathology generation.<n>PathAR stabilizes morphology under heterogeneous modality-specific appearances and enables spatially aligned image-mask pair generation.
  arXiv  Detail & Related papers  (2026-06-01T01:43:48Z)
• Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation [1.9336815376402718]
  We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation.<n>The proposed method integrates a novel tooth-specific topological loss into quantization-aware training.<n> Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models.
  arXiv  Detail & Related papers  (2026-05-05T18:42:15Z)
• Structural Connectome Harmonization Using Deep Learning: The Strength of Graph Neural Networks [0.9663199711697325]
  Small sample sizes in structural connectome (SC) studies limit the development of reliable biomarkers for neurological and psychiatric disorders.<n>Large-scale multi-site studies have exist, but they have acquisition-related biases due to scanner heterogeneity.<n>We propose a site-conditioned deep harmonization framework that harmonizes SCs across diverse acquisition sites without requiring metadata.
  arXiv  Detail & Related papers  (2025-07-18T14:58:05Z)
• HUG-VAS: A Hierarchical NURBS-Based Generative Model for Aortic Geometry Synthesis and Controllable Editing [4.285436540597423]
  We introduce HUG-VAS, a NURBS Generative model for Vascular geometry Synthesis.<n>It integrates NURBS surface parameterization with diffusion-based generative modeling to synthesize realistic, fine-grained aortic geometries.<n>HuG-VAS generates anatomically faithful aortas with supra-aortic branches, yielding biomarker distributions that closely match those of the original dataset.
  arXiv  Detail & Related papers  (2025-07-15T16:45:43Z)
• High-Fidelity Scientific Simulation Surrogates via Adaptive Implicit Neural Representations [51.90920900332569]
  Implicit neural representations (INRs) offer a compact and continuous framework for modeling spatially structured data.<n>Recent approaches address this by introducing additional features along rigid geometric structures.<n>We propose a simple yet effective alternative: Feature-Adaptive INR (FA-INR)
  arXiv  Detail & Related papers  (2025-06-07T16:45:17Z)
• ToothForge: Automatic Dental Shape Generation using Synchronized Spectral Embeddings [0.4799822253865054]
  ToothForge is a spectral approach for automatically generating novel 3D teeth.<n> generating shape spectra comes with the instability of the decomposed harmonics.<n> synchronized modeling removes the limiting factor imposed by previous methods.
  arXiv  Detail & Related papers  (2025-06-03T09:56:22Z)
• JADE: Joint-aware Latent Diffusion for 3D Human Generative Modeling [62.77347895550087]
  We introduce JADE, a generative framework that learns the variations of human shapes with fined-grained control.<n>Our key insight is a joint-aware latent representation that decomposes human bodies into skeleton structures.<n>To generate coherent and plausible human shapes under our proposed decomposition, we also present a cascaded pipeline.
  arXiv  Detail & Related papers  (2024-12-29T14:18:35Z)
• Latent Semantic Consensus For Deterministic Geometric Model Fitting [109.44565542031384]
  We propose an effective method called Latent Semantic Consensus (LSC) LSC formulates the model fitting problem into two latent semantic spaces based on data points and model hypotheses. LSC is able to provide consistent and reliable solutions within only a few milliseconds for general multi-structural model fitting.
  arXiv  Detail & Related papers  (2024-03-11T05:35:38Z)
• An End-to-End Deep Learning Generative Framework for Refinable Shape Matching and Generation [45.820901263103806]
  Generative modelling for shapes is a prerequisite for In-Silico Clinical Trials (ISCTs) We develop a novel unsupervised geometric deep-learning model to establish refinable shape correspondences in a latent space. We extend our proposed base model to a joint shape generative-clustering multi-atlas framework to incorporate further variability.
  arXiv  Detail & Related papers  (2024-03-10T21:33:53Z)

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.