Enhancement of guided thermal image super-resolution approaches

PL Suárez, D Carpio, AD Sappa - Neurocomputing, 2024 - Elsevier
Guided image processing techniques are widely used to extract meaningful information from
a guiding image and facilitate the enhancement of the guided one. This paper specifically …

Depth Map Estimation from a Single 2D Image

PL Suárez, D Carpio, A Sappa - 2023 17th International …, 2023 - ieeexplore.ieee.org
This paper presents an innovative architecture based on a Cycle Generative Adversarial
Network (CycleGAN) for the synthesis of high-quality depth maps from monocular images …

Boosting Guided Super-Resolution Performance with Synthesized Images

PL Suárez, D Carpio, A Sappa - 2023 17th International …, 2023 - ieeexplore.ieee.org
Guided image processing techniques are widely used for extracting information from a
guiding image to aid in the processing of the guided one. These images may be sourced …

Depth-Conditioned Thermal-like Image Generation

PL Suárez, A Sappa - 2024 14th International Conference on …, 2024 - ieeexplore.ieee.org
This paper proposes a novel approach to generate thermal-like representations from RGB
images by using the corresponding depth map as an additional constraint. The given RGB …

A Deep Learning Based Approach for Synthesizing Realistic Depth Maps

PL Suárez, D Carpio, A Sappa - International Conference on Image …, 2023 - Springer
This paper presents a novel cycle generative adversarial network (CycleGAN) architecture
for synthesizing high-quality depth maps from a given monocular image. The proposed …

[PDF][PDF] A Generative Model for Guided Thermal Image Super-Resolution

PL Suárez, AD Sappa - Proceedings Copyright, 2024 - refbase.cidis.espol.edu.ec
This paper presents a novel approach for thermal super-resolution based on a fusion prior,
low-resolution thermal image and H brightness channel of the corresponding visible …

[PDF][PDF] for SynthesizingRealisticDepthMaps

PL Suárez, DC AngelSappa - refbase.cidis.espol.edu.ec
This paper presents a novel cycle generative adversarial network (CycleGAN) architecture
for synthesizing high-quality depth maps from a given monocular image. The proposed …