3 papers
cs.CV2026
EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion
Johny J. Lopez, Md Meftahul Ferdaus, Mahdi Abdelguerfi +4
Depth completion from sparse LiDAR measurements and corresponding RGB images is a prerequisite for accurate 3D perception in robotic systems. Existing methods achieve high accuracy…
cs.CV2026
Edge-Optimized Vision-Language Models for Underground Infrastructure Assessment
Johny J. Lopez, Md Meftahul Ferdaus, Mahdi Abdelguerfi
Autonomous inspection of underground infrastructure, such as sewer and culvert systems, is critical to public safety and urban sustainability. Although robotic platforms equipped w…
cs.CV2023
Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation
Rasha Alshawi, Md Tamjidul Hoque, Md Meftahul Ferdaus +7
The proposed architecture, Dual Attentive U-Net with Feature Infusion (DAU-FI Net), addresses challenges in semantic segmentation, particularly on multiclass imbalanced datasets wi…