In this section, we first present an overview of 4 different architectures for neural implicit scene representations anddetails ofMulti-Res. See Figure 1 for an overview over the architectures. More specifically, each grid contains up toT feature vectors with dimensionalityF. We further reportNormal Consistencyfor the Replica dataset following [9,13,18,19,23,32] as near-perfect ground truth is available. We observe that using more input views for training improves reconstruction quality.

Subsampling involves creating smaller datasets by randomly selecting a subset of the original data points.

In this case, one can hardly distinguish non-robust data with LPS being 10 and safe data that are insensitive to be attacked.

Modern large scale datasets are often plagued with missing entries. For tabular data with missing values, a flurry of imputation algorithms solve for a complete matrix which minimizes some penalized reconstruction error. However, almost none of them can estimate the uncertainty of its imputations. This paper proposes a probabilistic and scalable framework for missing value imputation with quantified uncertainty.