Omar A. Mures
Omar A. Mures
Home
Publications
Contact
Light
Dark
Automatic
article-journal
Should I render or should AI Generate? Crafting Synthetic Semantic Segmentation Datasets with Controlled Generation
This work explores the integration of generative AI models for automatically generating synthetic image-labeled data. Our approach leverages controllable Diffusion Models to generate synthetic variations of semantically labeled images. Synthetic datasets for semantic segmentation struggle to represent real-world subtleties, such as different weather conditions or fine details, typically relying on costly simulations and rendering. However, Diffusion Models can generate diverse images using input text prompts and guidance images, like semantic masks. Our work introduces and tests a novel methodology for generating labeled synthetic images, with an initial focus on semantic segmentation, a demanding computer vision task.
Omar A. Mures
,
Manuel Silva
,
Manuel Lijó-Sanchez
,
Emilio J. Padrón
,
Jose A. Iglesias-Guitian
PDF
Cite
DOI
Exploring the effects of synthetic data generation: a case study on autonomous driving for semantic segmentation
Rendering 3D virtual scenarios has become a popular alternative for generating per-pixel-labeled image datasets, especially in fields like autonomous driving. The approach is valuable for training neural perception models, such as semantic segmentation models, particularly when data might be scarce, expensive, or difficult to collect. However, fundamental questions persist within the research community regarding the generation and processing of these synthetic images, particularly a better understanding of the key factors influencing the performance of deep learning models trained with such synthetic images.
Manuel Silva
,
Antonio Seoane
,
Omar A. Mures
,
Antonio M. López
,
Jose A. Iglesias-Guitian
PDF
Cite
DOI
Aeroelastic force prediction via temporal fusion transformers
Aero-structural shape design and optimization of bridge decks rely on accurately estimating their self-excited aeroelastic forces within the design domain. The inherent nonlinear features of bluff body aerodynamics and the high cost of wind tunnel tests and computational fluid dynamics (CFD) simulations make their emulation as a function of deck shape and reduced velocity challenging. We propose a time domain emulation strategy harnessing temporal fusion transformers (TFTs) to predict the self-excited forces time series before their integration into FDs.
Miguel Cid Montoya
,
Ashustosh Mishra
,
Sumit Verma
,
Omar A. Mures
,
Carlos E. Rubio‐Medrano
PDF
Cite
DOI
PlayNet: real-time handball play classification with Kalman embeddings and neural networks
Real-time play recognition and classification algorithms are crucial for automating video production and live broadcasts of sporting events. However, current methods relying on human pose estimation and deep neural networks introduce high latency on commodity hardware, limiting their usability in low-cost real-time applications. We present PlayNet, a novel approach to real-time handball play classification.
Omar A. Mures
,
Javier Taibo
,
Emilio J. Padrón
,
Jose A. Iglesias-Guitian
PDF
Cite
DOI
A Comprehensive Handball Dynamics Dataset for Game Situation Classification
This article presents a comprehensive dataset of labeled game situations obtained from multiple professional handball matches, which corresponds to the research paper entitled PlayNet: Real-time Handball Play Classification with Kalman Embeddings and Neural Networks. The dataset encompasses approximately 11 hours of footage from five handball games played in two different arenas, resulting in around 1 million data frames.
Omar A. Mures
,
Javier Taibo
,
Emilio J. Padrón
,
Jose A. Iglesias-Guitian
PDF
Cite
DOI
An application of fish detection based on eye search with artificial vision and artificial neural networks
A fish can be detected by means of artificial vision techniques, without human intervention or handling the fish. This work presents an …
Ángel J. Rico-Dı́az
,
Juan R. Rabuñal
,
Marcos Gestal
,
Omar A. Mures
,
Jerónimo Puertas
PDF
Cite
DOI
Assisted surface redesign by perturbing its point cloud representation
This research study explores the use of point clouds for design geometrically complex surfaces based on genetic morphogenesis. To this …
Rafael Iván Pazos-Pérez
,
Adrian Carballal
,
Juan R. Rabuñal
,
Omar A. Mures
,
María D. Garcı́a-Vidaurrázaga
PDF
Cite
DOI
Predicting vertical urban growth using genetic evolutionary algorithms in Tokyo’s Minato ward
This article explores the use of evolutionary genetic algorithms to predict scenarios of urban vertical growth in large urban centers. …
Rafael Iván Pazos-Pérez
,
Adrian Carballal
,
Juan R. Rabuñal
,
Omar A. Mures
,
María D. Garcı́a-Vidaurrázaga
PDF
Cite
DOI
Cite
×