During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a signiﬁcant waste of computation, especially for minor editing operations. In this work, we present Spatially Sparse Inference (SSI), a general-purpose technique that selectively performs computation for edited regions and accelerates various generative models, including both conditional GANs and diffusion models. Our key observation is that users tend to make gradual changes to the input image. This motivates us to cache and reuse the feature maps of the original image.
2022: Muyang Li, Ji Lin, Chenlin Meng, S. Ermon, Song Han, Junyan Zhu