ECE Seminar Series

Details

Title: Texture-Aware Representation Learning for Remote Sensing Image Classification and 3D Scene Reconstruction

Abstract: Texture cues play a central role in visual understanding, yet modern deep learning models often struggle to preserve both fine-scale and global structural information across diverse tasks. This talk presents recent advances in texture-aware representation learning that improve visual understanding across remote sensing image classification and 3D scene reconstruction. First, we introduce Neighborhood Feature Pooling (NFP), a lightweight architectural layer that enhances texture modeling by explicitly capturing local relational structure within feature representations. Easily integrated into existing deep networks, NFP improves remote sensing image classification by emphasizing subtle spatial patterns as well as improving class compactness and separability. Second, we present a wavelet-enhanced 3D Gaussian Splatting framework that addresses the challenge of reconstructing high-frequency detail under sparse or challenging imaging conditions. By incorporating Discrete Wavelet Transform–based supervision, the approach encourages representations that better preserve edges and structural geometry during reconstruction. Together, these works demonstrate how texture-aware learning principles can bridge recognition and reconstruction tasks, pointing toward richer texture-driven representations for remote sensing and beyond.

Bio: Dr. Joshua Peeples is an Assistant Professor in the Department of Electrical and Computer Engineering at Texas A&M University. Dr. Peeples received his Bachelor of Science degree in electrical engineering with a minor in mathematics from the University of Alabama at Birmingham. He earned his Ph.D. in the Department of Electrical and Computer Engineering at the University of Florida. Dr. Peeples has developed and refined novel deep learning methods for texture characterization, segmentation, and classification of images. His current research seeks to extend this work and explore new aspects such as developing algorithms for explainable artificial intelligence and various real-world applications in several domains. These methods can then be applied toward automated image understanding, object detection, and classification. Dr. Peeples has been recognized with several awards and positions, including the National Science Foundation Graduate Research Fellowship, United States Air Force Summer Faculty Fellowship, Massachusetts Institute of Technology Lincoln Laboratory Summer Visiting Scientist, and Joint Appointee at Los Alamos National Laboratory as a Guest Scientist in the Space Remote Sensing and Data Science group. He also serves as the Coordinator for the undergraduate machine learning course in the TAMU ECE Department and is an inaugural TAMU Honors Academy Honors Aggie Core Values Faculty Fellow. In addition to research and teaching, Dr. Peeples is dedicated to service and advocacy for students at the university and in the community.