arXiv subjects

Luis A. Zavala-Mondragon

Publications and source records attributed to Luis A. Zavala-Mondragon.

3 recordsLinked to original sources

arXiv2026

Flow-TAG: Flow-based conditional latent transport for accurate spline approximation and data compression

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.

cs.CG↗

arXiv2026

ORCAS - Orthogonal Representation for Compression of distributed Acoustic Sensing

Distributed Acoustic Sensing (DAS) utilizes fiber-optic cables to create virtual sensor arrays that monitor vibrations and strain over long distances. DAS is particularly useful in remote seismic sensing and infrastructure protection but generates large data volumes that pose processing challenges. The paper presents Orthogonal Representation for Compression of distributed Acoustic Sensing (ORCAS), a framework designed for efficient compression of DAS signals. ORCAS employs a learned orthogonal transform for swift sparse encoding, delivering over 250 MB/s throughput. It also includes a DAS-specific coding scheme, optimizing quantization thresholds with the Lloyd-Max algorithm for improved data fidelity. The system achieves real-time throughput exceeding 90 MB/s and demonstrates superior rate-distortion performance compared to existing standards like JPEG2000 and ZFP. Compression ratios reach around 13, with SNR and PSNR values supporting 13 dB and 28 dB. Evaluations are based on a diverse, publicly sourced DAS dataset.

eess.SP↗

arXiv2026

Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications

Numerous modern applications in signal processing and medical imaging necessitate acquiring high-dimensional signals under tight resource constraints. Traditional sampling theory suggests that accurate signal reconstruction requires a number of measurements proportional to the signal's ambient dimension, a requirement often too expensive or impractical. Compressed sensing challenges this notion by demonstrating that sparse signals can be recovered with fewer measurements, provided the measurement operator meets certain conditions. This proof-of-concept study presents a task-aware flow-based generative framework -- a reformulation of the conventional Flow Matching training paradigm with a flow model trained to optimize subsampling in compressed sensing applications. We establish the fundamental feasibility of the proposed framework of learning subsampling masks that substantially enhance the performance of compressed sensing for image classification, image reconstruction, and MRI acceleration. For the image reconstruction task, our method demonstrated state-of-the-art performance, achieving Peak Signal-to-Noise Ratio of 25.17 dB at the subsampling rate of 5\% on the CelebA dataset and 29.24 dB when reconstructing $8\times$ accelerated MRI measurements (fastMRI dataset) with the minimal computational overhead. These results highlight the effectiveness of task-conditioning within generative flow models and reveal a promising direction for representation learning strategies. Overall, the proposed framework offers a unified, flexible approach to designing data- and task-driven sensing schemes that can be potentially adapted to a broad range of inverse problems.

cs.CV↗