NARVis: Neural Accelerated Rendering for Real-Time Scientific Point Cloud Visualization
A high-quality neural renderer for visualizing a variety of large scientific point clouds with low motion-to-photon latency.
I am a research assistant at UMIACS working with Prof. Matthias Zwicker on efficient neural rendering solutions for point cloud visualization. My broader research interests lie at the intersection of 3D Vision and Computer Graphics with applications to mixed reality (AR/VR/XR) and scientific visualization. I previously worked at TCS Research with Dr. Lovekesh Vig and Ms. Ramya Hebbalaguppe on designing deep learning solutions for AR. I completed my undergraduate study in Computer Science and Engineering at IIITD where I collaborated with Prof. Saket Anand and Prof. Ojaswa Sharma on scene reconstruction and procedural modeling.
CV (as of Sep-2024).
_____
A high-quality neural renderer for visualizing a variety of large scientific point clouds with low motion-to-photon latency.
Augmenting the knowledge distillation framework with sparsity inducing ability of variational inference to learn compact and sparser networks.
A situated visualization method for overlay placement in AR and video applications respecting proximity to the object of interest, non-occlusion, and aesthetics.
Proposes a method for real-time gesture interaction for AR with egocentric view.