Fig. 9: Sample sparsity and testing performance.

a Quantitative comparison of testing performance in terms of sparsity, and cross-domain generalization result of (b) the baseline model (21 M) and (c) the proposed RNN (21 M). d Qualitative comparison of a volumetric reconstruction for different cases of training and testing conditions in terms of sparsity. For more details, see Table S1 in SI Section S1