Article

UnderwaterImage2IR: Underwater Impulse Response Generation via Dual-Path Pre-trained Networks and CGAN

2024-06-15

Abstract excerpt

In the field of acoustic simulation, methods that are widely applied and have been proven to be highly effective rely on accurately capturing the impulse response (IR) and its convolution relationship. This paper introduces a novel approach, named as UnderwaterImage2IR, that generates acoustic IRs from underwater images using Dual-Path Pre-trained Networks. This technique aims to achieve cross-modal conversion fro...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 4332c1d4-4c97-5a01-b2f2-d99565d05d39
DOI: 10.22541/au.171842605.50472215/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

UnderwaterImage2IR: Underwater Impulse Response Generation via Dual-Path Pre-trained Networks and CGANDOI 10.22541/au.171842605.50472215/v1Read

Integration of sonar and optical camera images using deep neural network for fish monitoringSemantic proximity Read

Bidirectional Generative Adversarial Representation Learning for Natural Stimulus SynthesisSemantic proximity Read

LPGAN: A LBP-based Proportional Input Generative Adversarial Network for Image FusionSemantic proximity Read

Dialectical GAN for SAR Image Translation: From Sentinel-1 to TerraSAR-XSemantic proximity Read

IterVocoder: Fast High-Fidelity Speech Synthesis via GAN-Guided Iterative RefinementSemantic proximity Read

A Real-Time Motion Deblurring Network for Sports- Related Dynamic Scenes Based on Lightweight GANSemantic proximity Read

Digital Inpainting of Mural Images Based on DC-CycleGANSemantic proximity Read

A Quality Metric for Semantically Transmitted Images in Machine-to-Machine CommunicationsSemantic proximity Read

Research on Dunhuang Murals Image Restoration Method Based on Generative Adversarial NetworkSemantic proximity Read

End-to-end deep image reconstruction from human brain activitySemantic proximity Read

Cycle-consistent Generative Adversarial Networks (CycleGANs) for the Non-Parallel Creation of Fake Voice MediaSemantic proximity Read

Mural inpainting via two-stage generative adversarial networkSemantic proximity Read