5 papers
Tracking by Predicting 3-D Gaussians Over Time
Tanish Baranwal, Himanshu Gaurav Singh, Jathushan Rajasegaran +1
We propose Video Gaussian Masked Autoencoders (Video-GMAE), a self-supervised approach for representation learning that encodes a sequence of images into a set of Gaussian splats m…
VROOM - Visual Reconstruction over Onboard Multiview
Yajat Yadav, Varun Bharadwaj, Jathin Korrapati +1
We introduce VROOM, a system for reconstructing 3D models of Formula 1 circuits using only onboard camera footage from racecars. Leveraging video data from the 2023 Monaco Grand Pr…
Fault-Tolerant IoT System Using Software-Based "Digital Twin"
Tanish Baranwal, Srihari Varada, Santanu Das +1
In this article, we present a novel redundancy scheme to realize a fault-tolerant IoT structure for application in high-reliability systems. The proposed fault-tolerant structure u…
Machine Learning-Based Anomaly Detection of Correlated Sensor Data: An Integrated Principal Component Analysis-Autoencoder Approach
Tanish Baranwal, Arnab Das, Srihari Varada +2
The growing adoption of IoT systems in industries like transportation, banking, healthcare, and smart energy has increased reliance on sensor networks. However, anomalies in sensor…
Discrete vs. Continuous Trade-offs for Generative Models
Jathin Korrapati, Tanish Baranwal, Rahul Shah
This work explores the theoretical and practical foundations of denoising diffusion probabilistic models (DDPMs) and score-based generative models, which leverage stochastic proces…