Papers › Unsupervised Portrait Shadow Removal via Generative Priors

Unsupervised Portrait Shadow Removal via Generative Priors

7 Aug 2021arXiv:2108.03466archive 2025-07-28

Yingqing He, Yazhou Xing, Tianjia Zhang, Qifeng Chen

Portrait images often suffer from undesirable shadows cast by casual objects or even the face itself. While existing methods for portrait shadow removal require training on a large-scale synthetic dataset, we propose the first unsupervised method for portrait shadow removal without any training data. Our key idea is to leverage the generative facial priors embedded in the off-the-shelf pretrained StyleGAN2. To achieve this, we formulate the shadow removal task as a layer decomposition problem: a shadowed portrait image is constructed by the blending of a shadow image and a shadow-free image. We propose an effective progressive optimization algorithm to learn the decomposition process. Our approach can also be extended to portrait tattoo removal and watermark removal. Qualitative and quantitative experiments on a real-world portrait shadow dataset demonstrate that our approach achieves comparable performance with supervised shadow removal methods. Our source code is available at https://github.com/YingqingHe/Shadow-Removal-via-Generative-Priors.

PaperPDFCode

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

Code

yingqinghe/shadow-removal-via-generative-priors officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

Shadow RemovalUnsupervised Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ConvolutionPath Length RegularizationR1 RegularizationWeight Demodulation

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