A cGAN denoiser on three orthogonal planes plus an LDGCNN recognizer is reported to improve noisy 3D face recognition accuracy by up to 14.81% over prior methods on Bosphorus.
Experimental Settings The proposed method is evaluated on the Bosphorus dataset [19], a commonly used 3D face point cloud dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Face recognition on point cloud with cgan-top for denoising
A cGAN denoiser on three orthogonal planes plus an LDGCNN recognizer is reported to improve noisy 3D face recognition accuracy by up to 14.81% over prior methods on Bosphorus.