Learning-based density-equalizing map

2025-06-10

AI Summary

Traditional density-equalizing maps (DEMs) suffer from low accuracy, overlapping artifacts, and prohibitive algorithmic restructuring for 2D→3D generalization. This paper introduces the first end-to-end learnable, density-driven shape deformation framework that employs deep neural networks to compute bijective parameterizations where surface area precisely reflects input density. Methodologically, we propose a joint loss combining density consistency and geometric regularity; incorporate a coarse-to-fine hierarchical transformation predictor to ensure bijectivity and robustness; and integrate differentiable rendering for auxiliary supervision. Our approach achieves significant improvements in mapping accuracy and overlap-free guarantee across diverse, complex density fields. It supports surface remeshing and generalizes seamlessly to both 2D and 3D domains without architectural or loss-function modifications.

Technology Category

• Machine Learning: Learning with Manifolds
• Computer Vision: 3D Computer Vision
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• 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
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Density-equalizing map (DEM) serves as a powerful technique for creating shape deformations with the area changes reflecting an underlying density function. In recent decades, DEM has found widespread applications in fields such as data visualization, geometry processing, and medical imaging. Traditional approaches to DEM primarily rely on iterative numerical solvers for diffusion equations or optimization-based methods that minimize handcrafted energy functionals. However, these conventional techniques often face several challenges: they may suffer from limited accuracy, produce overlapping artifacts in extreme cases, and require substantial algorithmic redesign when extended from 2D to 3D, due to the derivative-dependent nature of their energy formulations. In this work, we propose a novel learning-based density-equalizing mapping framework (LDEM) using deep neural networks. Specifically, we introduce a loss function that enforces density uniformity and geometric regularity, and utilize a hierarchical approach to predict the transformations at both the coarse and dense levels. Our method demonstrates superior density-equalizing and bijectivity properties compared to prior methods for a wide range of simple and complex density distributions, and can be easily applied to surface remeshing with different effects. Also, it generalizes seamlessly from 2D to 3D domains without structural changes to the model architecture or loss formulation. Altogether, our work opens up new possibilities for scalable and robust computation of density-equalizing maps for practical applications.

Problem

• Improving accuracy and avoiding overlaps in density-equalizing maps
• Extending 2D methods to 3D without structural changes
• Enhancing density uniformity and geometric regularity in mappings

Innovation

• Learning-based framework using deep neural networks
• Hierarchical approach for coarse and dense transformations
• Seamless generalization from 2D to 3D domains