FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation

• URL: http://arxiv.org/abs/2603.23199v1
• Date: Tue, 24 Mar 2026 13:45:39 GMT
• Title: FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
• Abstract summary: Deep learning-based 3D medical image segmentation methods relies on large-scale labeled datasets.<n>Formula-Driven Supervised Learning method offers an appealing alternative by generating training data and labels directly from mathematical formulas.<n>We introduce Formula-Driven supervised learning with Implicit Functions (FDIF), a framework that enables scalable pre-training without using any real data and medical expert annotations.
• Score: 15.58096401866496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning-based 3D medical image segmentation methods relies on large-scale labeled datasets, yet acquiring such data is difficult due to privacy constraints and the high cost of expert annotation. Formula-Driven Supervised Learning (FDSL) offers an appealing alternative by generating training data and labels directly from mathematical formulas. However, existing voxel-based approaches are limited in geometric expressiveness and cannot synthesize realistic textures. We introduce Formula-Driven supervised learning with Implicit Functions (FDIF), a framework that enables scalable pre-training without using any real data and medical expert annotations. FDIF introduces an implicit-function representation based on signed distance functions (SDFs), enabling compact modeling of complex geometries while exploiting the surface representation of SDFs to support controllable synthesis of both geometric and intensity textures. Across three medical image segmentation benchmarks (AMOS, ACDC, and KiTS) and three architectures (SwinUNETR, nnUNet ResEnc-L, and nnUNet Primus-M), FDIF consistently improves over a formula-driven method, and achieves performance comparable to self-supervised approaches pre-trained on large-scale real datasets. We further show that FDIF pre-training also benefits 3D classification tasks, highlighting implicit-function-based formula supervision as a promising paradigm for data-free representation learning. Code is available at https://github.com/yamanoko/FDIF.

Related papers

• Conditional Imputation for Within-Modality Missingness in Multi-Modal Federated Learning [8.35064965629059]
  Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative training.<n>Real-world clinical applications often suffer from within-modality missingness caused by sensor intermittency or irregular sampling.<n>We propose CondI, a framework explicitly addressing this missingness using conditional diffusion models.
  arXiv  Detail & Related papers  (2026-04-25T02:35:08Z)
• MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models [59.180043227905294]
  We propose MedPruner, a training-free and model-agnostic hierarchical token pruning framework for efficient 3D medical image understanding.<n>We show that MedPruner enables models such as MedGemma to maintain or even exceed their original performance while retaining fewer than 5% of visual tokens.
  arXiv  Detail & Related papers  (2026-03-12T07:37:00Z)
• MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts [50.37005070020306]
  MoRE is a dense 3D visual foundation model based on a Mixture-of-Experts (MoE) architecture.<n>MoRE incorporates a confidence-based depth refinement module that stabilizes and refines geometric estimation.<n>It integrates dense semantic features with globally aligned 3D backbone representations for high-fidelity surface normal prediction.
  arXiv  Detail & Related papers  (2025-10-31T06:54:27Z)
• Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Integration [15.929511077091687]
  We propose FlexMol, a flexible molecule pre-training framework that learns unified molecular representations while supporting single-modality input.<n>Our approach employs separate models for 2D and 3D molecular data, leverages parameter sharing to improve computational efficiency, and utilizes a decoder to generate features for the missing modality.
  arXiv  Detail & Related papers  (2025-10-08T14:02:51Z)
• SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion [52.959716866316604]
  Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems.<n>We propose the Semantic-PHysical Engaged REpresentation (SPHERE) for camera-based SSC.<n>SPHERE integrates voxel and Gaussian representations for joint exploitation of semantic and physical information.
  arXiv  Detail & Related papers  (2025-09-14T09:07:41Z)
• F-INR: Functional Tensor Decomposition for Implicit Neural Representations [7.183424522250937]
  Implicit Representation (INR) has emerged as a powerful tool for encoding discrete signals into continuous, differentiable functions using neural networks.<n>We propose F-INR, a framework that reformulates INR learning through functional decomposition, breaking down high-dimensional tasks into lightweight, axis-specific sub-networks.
  arXiv  Detail & Related papers  (2025-03-27T13:51:31Z)
• NF-SLAM: Effective, Normalizing Flow-supported Neural Field representations for object-level visual SLAM in automotive applications [20.963261049295085]
  We propose a vision-only object-level SLAM framework for automotive applications representing 3D shapes by implicit signed distance functions.<n>Our key innovation consists of augmenting the standard neural representation by a normalizing flow network.<n>The newly proposed architecture exhibits a significant performance improvement in the presence of only sparse and noisy data.
  arXiv  Detail & Related papers  (2025-03-14T08:46:56Z)
• DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification [11.194964108429252]
  DeepFRC is an end-to-end deep learning framework that jointly learns warping functions and a classification within a unified architecture.<n>We provide the first theoretical guarantees for such a joint model, proving its ability to approximate optimal warpings.<n>Experiments on synthetic and real-world datasets demonstrate that DeepFRC consistently outperforms state-of-the-art methods in both alignment quality and classification accuracy.
  arXiv  Detail & Related papers  (2025-01-30T03:35:03Z)
• Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries [8.732260277121547]
  Implicit Neural Representations have gained prominence as a powerful framework for capturing complex data modalities. Within the realm of 3D shape representation, Neural Signed Distance Functions (SDF) have demonstrated remarkable potential in faithfully encoding intricate shape geometry.
  arXiv  Detail & Related papers  (2024-08-27T14:54:33Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models [83.35835521670955]
  Surf-D is a novel method for generating high-quality 3D shapes as Surfaces with arbitrary topologies. We use the Unsigned Distance Field (UDF) as our surface representation to accommodate arbitrary topologies. We also propose a new pipeline that employs a point-based AutoEncoder to learn a compact and continuous latent space for accurately encoding UDF.
  arXiv  Detail & Related papers  (2023-11-28T18:56:01Z)
• Interpretable 2D Vision Models for 3D Medical Images [47.75089895500738]
  This study proposes a simple approach of adapting 2D networks with an intermediate feature representation for processing 3D images. We show on all 3D MedMNIST datasets as benchmark and two real-world datasets consisting of several hundred high-resolution CT or MRI scans that our approach performs on par with existing methods.
  arXiv  Detail & Related papers  (2023-07-13T08:27:09Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Representation-Agnostic Shape Fields [43.123829024621514]
  We present Representation-Agnostic Shape Fields (RASF), a generalizable and computation-efficient shape embedding module for 3D deep learning. Based on RASF, shape embeddings for various 3D shape representations (point clouds, meshes and voxels) are retrieved by coordinate indexing. Once trained, RASF becomes a plug-and-play performance booster with negligible cost.
  arXiv  Detail & Related papers  (2022-03-19T06:54:45Z)
• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes [86.2129580231191]
  Adjoint Rigid Transform (ART) Network is a neural module which can be integrated with a variety of 3D networks. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks. We will release our code and pre-trained models for further research.
  arXiv  Detail & Related papers  (2021-02-01T20:58:45Z)

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.