arXiv subjects

Daniel Torres

Publications and source records attributed to Daniel Torres.

7 recordsLinked to original sources

arXiv2026

Variational Deep Unfolding with Mamba-Based Nonlocal Modeling for Underwater Image Enhancement

Underwater imaging plays a crucial role in ocean engineering, although captured data often suffer from poor visibility and color distortion. To address these challenges, we propose a model-based deep unfolding network for underwater image enhancement that integrates variational modeling into a learnable architecture. The framework is guided by a variational formulation based on a dehazing decomposition, incorporating a multiplicative residual component to absorb remaining artifacts and a nonlocal gradient-type constraint to preserve structural details and enhance edge sharpness. We provide a theoretical analysis establishing the existence of solution for the associated minimization problem. The proposed unfolding method incorporates Mamba layers to efficiently capture self-similarities in the scene. In addition, we introduce a proximal trajectory loss that enforces consistency between the unfolding stages and the iterations of an ideal restoration regularizer. Experimental results demonstrate that the proposed unfolding approach achieves improved visual quality and competitive quantitative performance compared with recent state-of-the-art methods. The source code will be available at https://github.com/MIA-UIB/Variational-Unfolding-Mamba-Underwater-Enhancement .

cs.CV↗

arXiv2026

Time-dependent metrics and connections

Time-dependent structures often appear in differential geometry, particularly in the study of non-autonomous differential equations on manifolds. One may study the geodesics associated with a time-dependent Riemannian metric by extremizing the corresponding energy functional, but also through the introduction of a more general concept of time-dependent covariant derivative operator. This relies on the examination of connections on the product manifold $\mathbb{R}\times M$. For these time-dependent covariant derivatives we explore the notions of parallel transport, geodesics and torsion. We also define the derivative of a one-parameter family of connections.

math.DG↗

arXiv2025

Super-Resolution of Sentinel-2 Images Using a Geometry-Guided Back-Projection Network with Self-Attention

The Sentinel-2 mission provides multispectral imagery with 13 bands at resolutions of 10m, 20m, and 60m. In particular, the 10m bands offer fine structural detail, while the 20m bands capture richer spectral information. In this paper, we propose a geometry-guided super-resolution model for fusing the 10m and 20m bands. Our approach introduces a cluster-based learning procedure to generate a geometry-rich guiding image from the 10m bands. This image is integrated into an unfolded back-projection architecture that leverages image self-similarities through a multi-head attention mechanism, which models nonlocal patch-based interactions across spatial and spectral dimensions. We also generate a dataset for evaluation, comprising three testing sets that include urban, rural, and coastal landscapes. Experimental results demonstrate that our method outperforms both classical and deep learning-based super-resolution and fusion techniques.

eess.IV↗

arXiv2025

Nonlocal Retinex-Based Variational Model and its Deep Unfolding Twin for Low-Light Image Enhancement

Images captured under low-light conditions present significant limitations in many applications, as poor lighting can obscure details, reduce contrast, and hide noise. Removing the illumination effects and enhancing the quality of such images is crucial for many tasks, such as image segmentation and object detection. In this paper, we propose a variational method for low-light image enhancement based on the Retinex decomposition into illumination, reflectance, and noise components. A color correction pre-processing step is applied to the low-light image, which is then used as the observed input in the decomposition. Moreover, our model integrates a novel nonlocal gradient-type fidelity term designed to preserve structural details. Additionally, we propose an automatic gamma correction module. Building on the proposed variational approach, we extend the model by introducing its deep unfolding counterpart, in which the proximal operators are replaced with learnable networks. We propose cross-attention mechanisms to capture long-range dependencies in both the nonlocal prior of the reflectance and the nonlocal gradient-based constraint. Experimental results demonstrate that both methods compare favorably with several recent and state-of-the-art techniques across different datasets. In particular, despite not relying on learning strategies, the variational model outperforms most deep learning approaches both visually and in terms of quality metrics.

cs.CV↗

arXiv2023

Flexible Supervised Autonomy for Exploration in Subterranean Environments

While the capabilities of autonomous systems have been steadily improving in recent years, these systems still struggle to rapidly explore previously unknown environments without the aid of GPS-assisted navigation. The DARPA Subterranean (SubT) Challenge aimed to fast track the development of autonomous exploration systems by evaluating their performance in real-world underground search-and-rescue scenarios. Subterranean environments present a plethora of challenges for robotic systems, such as limited communications, complex topology, visually-degraded sensing, and harsh terrain. The presented solution enables long-term autonomy with minimal human supervision by combining a powerful and independent single-agent autonomy stack, with higher level mission management operating over a flexible mesh network. The autonomy suite deployed on quadruped and wheeled robots was fully independent, freeing the human supervision to loosely supervise the mission and make high-impact strategic decisions. We also discuss lessons learned from fielding our system at the SubT Final Event, relating to vehicle versatility, system adaptability, and re-configurable communications.

cs.RO↗

arXiv2022

Lagrangian-Hamiltonian formalism for time-dependent dissipative mechanical systems

In this paper we present a unified Lagrangian--Hamiltonian geometric formalism to describe time-dependent contact mechanical systems, based on the one first introduced by K. Kamimura and later formalized by R. Skinner and R. Rusk. This formalism is especially interesting when dealing with systems described by singular Lagrangians, since the second-order condition is recovered from the constraint algorithm. In order to illustrate this formulation, some relevant examples are described in full detail: the Duffing equation, an ascending particle with time-dependent mass and quadratic drag, and a charged particle in a stationary electric field with a time-dependent constraint.

math-ph↗

arXiv2017

GalRotpy: an educational tool to understand and parametrize the rotation curve and gravitational potential of disk-like galaxies

\textbf{GalRotpy} is an educational \verb+Python3+-based visual tool, which is useful to undestand how is the contribution of each mass component to the gravitational potential of disc-like galaxies by means of their rotation curve. Besides, \textbf{GalRotpy} allows the user to perform a parametric fit of a given rotation curve, which relies on a MCMC procedure implemented by using \verb+emcee+ package. Here the gravitational potential of disc-like galaxies is built from the contribution of a Miyamoto-Nagai potential model for the bulge/core and the thin/thick disc, an exponential disc, together with the NFW (Navarro-Frenk- White) potential or the Burkert (cored density profile) potential for the Dark Matter halo, where each contribution is implemented by using \verb+galpy+ package. We summarize the properties of each contribution to the rotation curve involved, and then describe how \textbf{GalRotpy} is implemented along with its capabilities. Finally we present the characterization of two galaxies, NGC6361 and M33, and show that the results for M33 provided by \textbf{GalRotpy} are consistent with those found in the literature.

astro-ph.GA↗