Denoising of Photogrammetric Dummy Head Ear Point Clouds for Individual Head-Related Transfer Functions Computation

• DOI: 10.48550/arxiv.2408.16410
• Publication Date: 2024-08-29
• Authors: F Giusto; Francesc Lluís; Sjoerd van Ophem; Elke Deckers
• Keywords: FOS: Computer and information sciences; Sound (cs.SD); Audio and Speech Processing (eess.AS); FOS: Electrical engineering, electronic engineering, information engineering; Computer Science - Sound; Electrical Engineering and Systems Science - Audio and Speech Processing

Individual Head Related Transfer Functions (HRTFs), crucial for realistic virtual audio rendering, can be efficiently numerically computed on precise three-dimensional head and ear scans. While photogrammetry scanning is promising, it generally lacks in accuracy, leading to HRTFs showing significant perceptual deviation from reference data, owing the error mainly affecting most occluded pinna structures. This papers analyses use of Deep Neural Networks (DNNs) denoising photogrammetric Various DNNs, fine-tuned samples corrupted with modelled synthetic mimicking that observed dummy scans, are tested benchmarked against a classical approach. One DNN further modified retrained increase its performance. The original denoised scans compared those scan, best-performing capable decreasing levels obtained accurately measured individual data. Correlation analysis between geometrical metrics, scanned point clouds, related used identify relevant metrics assess target terms similarity them.