# Semantic Image Synthesis with Unconditional Generator Source: [Semantic Image Synthesis with Unconditional Generator]() Collection index: [llms.txt]() Data updated: 2026-01-04T05:02:20.328Z Authors: Jungwoo Chae, Hyunin Cho, Sooyeon Go, Kyungmook Choi, Youngjung Uh Published: 2024-02-22T09:10:28.000Z ## Abstract Semantic image synthesis (SIS) aims to generate realistic images that match given semantic masks. Despite recent advances allowing high-quality results and precise spatial control, they require a massive semantic segmentation dataset for training the models. Instead, we propose to employ a pre-trained unconditional generator and rearrange its feature maps according to proxy masks. The proxy masks are prepared from the feature maps of random samples in the generator by simple clustering. The feature rearranger learns to rearrange original feature maps to match the shape of the proxy masks that are either from the original sample itself or from random samples. Then we introduce a semantic mapper that produces the proxy masks from various input conditions including semantic masks. Our method is versatile across various applications such as free-form spatial editing of real images, sketch-to-photo, and even scribble-to-photo. Experiments validate advantages of our method on a range of datasets: human faces, animal faces, and buildings. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Semantic Image Synthesis on CelebAMask-HQ](): Semantic Image Synthesis; CelebAMask-HQ; FID: 18.5. ## Original sources and implementation [Original paper]() [PDF]()