Education

  • PhD in Computer Science UC Santa Barbara·2023–2027 (expected)
  • BTech (Bachelors of Technology) in Computer Science Indian Institute of Technology (IIT), Goa·2020

Honors & Awards

  • Outstanding TA Award Computer Science, UC Santa Barbara (2025)

Research Areas

We develop computer vision and XR systems that help people who are blind or have low vision navigate and understand real-world environments.

Apurv Varshney

Assistive Technology Computer Vision Blindness & Low Vision

Affiliated Research Areas

We use immersive VR, eye tracking, and mobile EEG to study how people navigate complex environments, how they use navigation aids, and why strategies and performance differ across individuals.

Software

BionicVisionXR is an open-source virtual reality toolbox for studying simulated prosthetic vision during natural head and body movement.

Apurv Varshney

Software Engineering Visual Prostheses Extended Reality

Publications

We evaluate head- and cane-mounted cameras for blind navigation and show that combining both yields superior spatial perception, guiding the design of hybrid, user-aligned assistive systems.

We compared three common guidance techniques for immersive VR wayfinding: a directional arrow, a minimap, and a compass.

We compared visual, auditory, and haptic out-of-view guidance during object search under simulated prosthetic vision, and found that the non-visual cues supported faster search than a visual cue competing for the same sparse phosphene bandwidth.

We examine whether stress exposure during environmental learning fosters resilience to stress in subsequent navigation or impairs learning.

We compare two complementary approaches to semantic preprocessing in immersive virtual reality: SemanticEdges, which highlights all relevant objects at once, and SemanticRaster, which staggers object categories over time to reduce visual clutter.

Using an immersive VR system, we systematically evaluated two behavioral tasks under four raster patterns (horizontal, vertical, checkerboard, and random) and found checkerboard raster to be the most effective.

We introduce a computational virtual patient (CVP) pipeline that integrates anatomically grounded phosphene simulation with task-optimized deep neural networks to forecast patient perceptual capabilities across diverse prosthetic designs and tasks.

We used immersive virtual reality to develop a novel behavioral paradigm to examine navigation under dynamically changing, high-stress situations.