Problem
Research questions and friction points this paper is trying to address.
curve fitting
B-spline approximation
data compression
ECG signals
noise robustness
Flow-TAG: Flow-based conditional latent transport for accurate spline approximation and data compression
🤖 AI Summary
This study addresses the challenge of robustly fitting B-spline models to noisy discrete data in computer-aided design. To this end, it proposes a novel latent transport framework based on generative flow models, which integrates a 1D U-Net backbone with conditional latent transport techniques to directly map curve geometries into an optimal parameter space. This framework significantly enhances noise resilience and generalization capability. Experimental results demonstrate that the fitting error is reduced by approximately 55% compared to state-of-the-art methods. Furthermore, when applied to electrocardiogram signal compression, the approach achieves a 13-fold compression ratio with only 5% distortion, effectively balancing high-precision curve fitting with efficient data compression.
📝 Abstract
Robust curve fitting is essential in computer-aided design for transforming noisy, discrete data into accurate geometric models that ensure numerical stability across engineering workflows. B-spline models have become the industry standard for this task, offering a flexible and reliable framework characterized by local control and smooth shape representation. This paper presents flow-TAG--a data-driven framework based on a generative flow model with a 1D U-Net backbone capable of mapping the geometry of a curve to the optimal parametrization for cubic B-splines. By leveraging learned geometric patterns, flow-TAG exhibits superior parameterization performance, robustness to noise in the input data, and strong generalization capability to previously unseen 2D and 3D curves drawn from distinct data distributions. Flow-TAG yields fitted curves that achieve the lower root-mean-square error (55% lower on average) and Hausdorff distance (52% lower on average) relative to state-of-the-art data-driven methods. In addition, we investigate the practical applicability of our generative framework in the compression of ECG signals for wearable devices. The proposed compression setup provides a compression ratio of 13 with the signal distortion of around 5%, which is acceptable in the field.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Generative Flow Model
B-spline Approximation
1D U-Net
Curve Fitting
Data Compression
🔎 Similar Papers
No similar papers found.
