5 papers · 1 filter
AI or Real: Detecting Partially Altered Videos Under Resource-Constrained Environments
Tamoghna Chakraborty, Md Nurul Absur, Sourya Saha +1
The proliferation of generative video models has shifted the practical detection threat from fully fabricated clips to partially manipulated footages. Although modern detectors ach…
Understanding Sensor Vulnerabilities in Industrial XR Tracking
Sourya Saha, Md. Nurul Absur
Extended Reality (XR) systems deployed in industrial and operational settings rely on Visual--Inertial Odometry (VIO) for continuous six-degree-of-freedom pose tracking, yet these…
Detection and Recovery of Adversarial Slow-Pose Drift in Offloaded Visual-Inertial Odometry
Soruya Saha, Md Nurul Absur, Saptarshi Debroy
Visual-Inertial Odometry (VIO) supports immersive Virtual Reality (VR) by fusing camera and Inertial Measurement Unit (IMU) data for real-time pose. However, current trend of offlo…
Reliable Multi-view 3D Reconstruction for `Just-in-time' Edge Environments
Md. Nurul Absur, Abhinav Kumar, Swastik Brahma +1
Multi-view 3D reconstruction applications are revolutionizing critical use cases that require rapid situational-awareness, such as emergency response, tactical scenarios, and publi…
Poster: Reliable 3D Reconstruction for Ad-hoc Edge Implementations
Md Nurul Absur, Swastik Brahma, Saptarshi Debroy
Ad-hoc edge deployments to support real-time complex video processing applications such as, multi-view 3D reconstruction often suffer from spatio-temporal system disruptions that g…