arxiv_cv 85% Match Research Paper Computer graphics researchers,Digital artists,Image processing engineers,Medical visualization specialists 1 day ago

Applying Medical Imaging Tractography Techniques to Painterly Rendering of Images

computer-vision › scene-understanding

📄 Abstract

Abstract: Doctors and researchers routinely use diffusion tensor imaging (DTI) and tractography to visualize the fibrous structure of tissues in the human body. This paper explores the connection of these techniques to the painterly rendering of images. Using a tractography algorithm the presented method can place brush strokes that mimic the painting process of human artists, analogously to how fibres are tracked in DTI. The analogue to the diffusion tensor for image orientation is the structural tensor, which can provide better local orientation information than the gradient alone. I demonstrate this technique in portraits and general images, and discuss the parallels between fibre tracking and brush stroke placement, and frame it in the language of tractography. This work presents an exploratory investigation into the cross-domain application of diffusion tensor imaging techniques to painterly rendering of images. All the code is available at https://github.com/tito21/st-python

Authors (1)

Alberto Di Biase

Submitted

November 1, 2025

arXiv Category

cs.GR

arXiv PDF Code

Key Contributions

This paper explores the novel application of medical imaging tractography techniques, specifically diffusion tensor imaging (DTI) and tractography algorithms, to the painterly rendering of images. It demonstrates how a tractography algorithm can be used to place brush strokes that mimic human artists' painting processes, utilizing the structural tensor for better local orientation information than gradients alone.

Business Value

Opens new avenues for creative tools in digital art and graphic design, potentially enabling artists to achieve unique styles and effects by leveraging advanced imaging concepts.

Paper Metadata

Innovation Type

Cross-domain Application/Novel Technique

Deployment Feasibility

High. The described method is algorithmic and can be implemented as a software tool or plugin.

Limitations Addressed

Lack of methods to mimic human artistic brush stroke placement,Limited use of medical imaging techniques in computer graphics

View Code on GitHub

Technical Tags

Painterly RenderingDiffusion Tensor Imaging (DTI)TractographyStructural TensorBrush Stroke PlacementImage OrientationGradient InformationArtistic Style TransferCross-domain application

Research Topics

Computer GraphicsImage SynthesisMedical Imaging TechniquesArtistic RenderingCross-disciplinary Research

Methods & Architectures

Tractography algorithmStructural tensor computationBrush stroke placement based on orientation Tractography-based rendering pipeline

Applications & Tasks

Computer Graphics Digital Art Medical Visualization (analogous) Mimicking human artist brush strokesApplying medical imaging techniques to image renderingImproving local orientation information for rendering Painterly renderingGenerating artistic imagesVisualizing image structure

Related Fields

Computer GraphicsMedical ImagingImage ProcessingArtComputational Photography

Keywords

Painterly RenderingTractographyDiffusion Tensor ImagingStructural TensorBrush StrokesImage SynthesisComputer GraphicsArtistic StyleCross-domainImage Orientation

Academic Context

#Computer Graphics#Image Synthesis#Medical Imaging Techniques#Artistic Rendering#Cross-disciplinary Research

Technology Stack

Frameworks & Libraries

Python (implied by GitHub)

Programming Languages

Python

Commercial Potential

Potential Products

Artistic rendering software pluginsDigital painting toolsImage stylization applications

Target Industries

Media and EntertainmentGraphic DesignAdvertisingGaming

Use Case Examples

Creating portraits with a unique, painterly styleGenerating stylized landscapesDeveloping tools for digital artists to explore new rendering techniques

Competitive Edge

Offers a novel approach to painterly rendering by drawing inspiration from medical imaging, potentially creating unique artistic outputs not achievable with traditional methods.

Market Opportunity

Niche but active market for creative software and digital art tools.

Revenue Models

Freemium model for softwarelicensing to creative software companies.

Resource Requirements

Compute Needs

Moderate, depending on image resolution and complexity of the tractography algorithm.

Data Requirements

Input images (portraits, general images).

Deployment Constraints

Computational efficiency for real-time rendering, user-friendliness of the interface.

Scalability

Scalability depends on the efficiency of the tractography implementation and the size of the input images.

Production Readiness

Maturity Level

Exploratory Research

Time to Market

1-2 years for a usable tool/plugin.

Licensing

Open Source (implied by GitHub availability)

Patent Potential

Low to moderate, depending on the novelty of the specific algorithmic implementation.

View Full Paper Back to Papers