Spatially Sparse Inference for Generative Image Editing 352 Supplementary Material 353 A Additional Implementation Details

We omit the element-wise operations for simplicity and follow the notations in Section 3 . As mentioned in Section 3.2, we fuse Note that the pre-computation is cheap and only needs to be once for each resolution. We elaborate more details on how we build the synthetic editing dataset. Figure 7 (a) shows some examples of our synthetic editing on LSUN Church. The detailed distribution is shown in Figure 8a .