A point-cloud reconstruction illuminated by optical and acoustic wavefronts

Ph.D. researcher · Arizona State University

I build imaging systems that see what conventional cameras cannot.

I’m Omkar Vengurlekar, a computational imaging researcher working across differentiable rendering, neural scene representations, time-of-flight sensing, and 3D reconstruction.

Time-of-flight Neural rendering Multimodal 3D

Patents

From research signals to protected systems.

Two U.S. provisional applications translate high-speed optical sensing and physics-guided 3D reconstruction into protectable technology.

View filing details
Patent pending U.S. provisional

MHz-Rate Optical Depth Imaging using Software-Defined Radios

InventorsAdithya Pediredla, Ramchander Bhaskara, Dhawal Sirikonda, Omkar Vengurlekar, Juhyeon Kim, Joseph Lazzaro, Suren Jayasuriya

Optical depth imagingSoftware-defined radioTime-of-flight
Patent pending U.S. provisional

Method for 3D Synthetic Aperture Sonar Reconstruction using Complex Spherical-Harmonic Scattering Fields

InventorsOmkar Vengurlekar, Adithya Pediredla, Suren Jayasuriya

3D reconstructionSpherical harmonicsNeural fields

Research spectrum

From physical signals to 3D understanding.

My work spans the full imaging pipeline: I build sensing hardware, model how signals propagate, write differentiable renderers, and optimize scene representations on the GPU.

01

Computational imaging

I design sensing systems that recover depth, vibration, and hidden structure from time-of-flight, Schlieren, and multi-camera measurements.

Time-of-flightScientific imagingTomographySensor fusion
02

Differentiable rendering

I connect physics-based image formation to optimization—building forward models, adjoints, and inverse renderers for optical and acoustic scenes.

Inverse renderingGaussian splattingNeural fieldsMitsuba / Dr.Jit
03

GPU reconstruction

I write custom CUDA and OptiX systems for high-throughput simulation, reconstruction, and analysis across unconventional sensing modalities.

CUDAOptiXPyTorch / JAXHigh-performance computing

Selected publications

Recent work

View all publications
2026 ACM Transactions on Graphics · SIGGRAPH Asia Featured

SDR-ToF: Million Optical Depth Samples per Second Using Software-Defined Radio

Ramchander Bhaskara*, Dhawal Sirikonda*, Omkar Vengurlekar*, Juhyeon Kim, Joseph Lazarro, Suren Jayasuriya, Adithya Pediredla

* Equal contribution

RF-coherent optical depth sensing with commodity software-defined radios at megahertz rates, enabling sub-millimeter precision, vibration analysis, audio recovery, and high-speed depth scanning.

Time-of-FlightOptical sensingRF systems
2026 13th International Conference on 3D Vision · Oral Featured

SH-SAS: An Implicit Neural Representation for Complex Spherical-Harmonic Scattering Fields for 3D Synthetic Aperture Sonar

Omkar Vengurlekar, Adithya Pediredla, Suren Jayasuriya

Neural fieldsSynthetic aperture sonar3D reconstruction
2025 IEEE Transactions on Pattern Analysis and Machine Intelligence Featured

Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion

Ziyuan Qu, Omkar Vengurlekar, Mohamad Qadri, Kevin Zhang, Michael Kaess, Christopher Metzler, Suren Jayasuriya, Adithya Pediredla

Gaussian splattingSensor fusionDifferentiable rendering

Research toolkit

Hardware, physics, code.

I own the pipeline from calibrated capture and signal processing to differentiable simulation and GPU reconstruction.

Sensing

ToF · Schlieren · RGB · Multimodal

Representation

Gaussian splats · Neural fields · Spherical harmonics

Compute

CUDA · OptiX · PyTorch · JAX · Dr.Jit

Open to research collaborations

Let’s build imaging systems for the signals cameras miss.

Start a conversation