Point Cloud Upsampling via Disentangled Refinement

Figure 1. In the top row, we show (a) a sparse real-scanned point set from [23], followed by upsampled results (16×) produced by (b) MPU [26], (c) PU-GAN [12], and (d) our method. In the bottom row, we show the associated reconstructed 3D meshes produced by the ball-pivoting algorithm [2]. Clearly, our method outperforms others on the local uniformity, contributing a better surface reconstruction.