AudioGS encodes sound fields as Audio Gaussians with dual spherical harmonic coefficients and decay terms to render binaural audio, reducing magnitude error by over 14% and perceptual error by 25% versus visual-guided baselines on Replay-NVAS.
Extending gaussian splatting to audio: Optimizing audio points for novel-view acoustic synthesis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AudioGS: Spectrogram-Based Audio Gaussian Splatting for Sound Field Reconstruction
AudioGS encodes sound fields as Audio Gaussians with dual spherical harmonic coefficients and decay terms to render binaural audio, reducing magnitude error by over 14% and perceptual error by 25% versus visual-guided baselines on Replay-NVAS.