Papers › Improved StyleGAN Embedding: Where are the Good Latents?

Improved StyleGAN Embedding: Where are the Good Latents?

13 Dec 2020arXiv:2012.09036archive 2025-07-28

Peihao Zhu, Rameen Abdal, Yipeng Qin, John Femiani, Peter Wonka

StyleGAN is able to produce photorealistic images that are almost indistinguishable from real photos. The reverse problem of finding an embedding for a given image poses a challenge. Embeddings that reconstruct an image well are not always robust to editing operations. In this paper, we address the problem of finding an embedding that both reconstructs images and also supports image editing tasks. First, we introduce a new normalized space to analyze the diversity and the quality of the reconstructed latent codes. This space can help answer the question of where good latent codes are located in latent space. Second, we propose an improved embedding algorithm using a novel regularization method based on our analysis. Finally, we analyze the quality of different embedding algorithms. We compare our results with the current state-of-the-art methods and achieve a better trade-off between reconstruction quality and editing quality.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ZPdesu/II2S officialmentioned on GitHubpytorch report
kkang831/BDInvert_Release mentioned on GitHubpytorchAGPL-3.0 report
yuval-alaluf/hyperstyle mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Diversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adaptive Instance NormalizationConvolutionDense ConnectionsFeedforward NetworkR1 RegularizationStyleGAN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections