Presentation

<
AONeuS: A Neural Rendering Framework for Acoustic-optical Sensor Fusion
SessionSound, Light, Radiofrequency
DescriptionUnderwater 3D surface reconstruction has broad applications. Often, submersibles must capture measurements from a small baseline. Small baselines make 3D reconstruction more challenging. We present an acoustic-optical neural surface reconstruction framework (AONeuS), which fuses complementary sonar and optical measurements to reconstruct accurate 3D surfaces from measurements captured over small baselines.
Authors
Mohamad Qadri
Carnegie Mellon University
Kevin Zhang
University of Maryland College Park
Akshay Hinduja
Carnegie Mellon University
Michael Kaess
Carnegie Mellon University
Adithya Pediredla
Dartmouth College
Christopher Metzler
University of Maryland College Park
Event Type
Technical Paper
TimeThursday, 1 August 20242:10pm - 2:20pm MDT
LocationMile High 3C
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Thursday, 1 August 20242:00pm - 3:30pm MDTMile High 3C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Fabrication
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Thursday
Next PresentationNext PresentationDiffSound: Differentiable Modal Sound Rendering and Inverse Rendering for Diverse Inference Tasks