Systematic Analysis and Removal of Circular Artifacts for StyleGAN
StyleGAN is one of the state-of-the-art image generators which is well-known for synthesizing high-resolution and hyper-realistic face images. Though images generated by vanilla StyleGAN model are visually appealing, they sometimes contain prominent circular artifacts which severely degrade the quality of generated images. In this work, we provide a systematic investigation on how those circular artifacts are formed by studying the functionalities of different stages of vanilla StyleGAN architecture, with both mechanism analysis and extensive experiments. The key modules of vanilla StyleGAN that promote such undesired artifacts are highlighted. Our investigation also explains why the artifacts are usually circular, relatively small and rarely split into 2 or more parts. Besides, we propose a simple yet effective solution to remove the prominent circular artifacts for vanilla StyleGAN, by applying a novel pixel-instance normalization (PIN) layer.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Counterfactual Explanations for Face Forgery Detection via Adversarial Removal of Artifacts
Highly realistic AI generated face forgeries known as deepfakes have raised serious social concerns. Although DNN-based face forgery detection models have achieved good performance, they are vulnerable to latest generati…
Adversarial AttackcounterfactualDifferentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal
Conebeam CT using a circular trajectory is quite often used for various applications due to its relative simple geometry. For conebeam geometry, Feldkamp, Davis and Kress algorithm is regarded as the standard reconstruct…
Deep LearningPerformance Comparison of Deep Learning Architectures for Artifact Removal in Gastrointestinal Endoscopic Imaging
Endoscopic images typically contain several artifacts. The artifacts significantly impact image analysis result in computer-aided diagnosis. Convolutional neural networks (CNNs), a type of deep learning, can removes such…
Think Twice Before Detecting GAN-Generated Fake Images From Their Spectral Domain Imprints
Accurate detection of the fake but photorealistic images is one of the most challenging tasks to address social, biometrics security and privacy related concerns in our community. Earlier research has underlined the …
Generative Adversarial NetworkRemoval of Ocular Artifacts in EEG Using Deep Learning
EEG signals are complex and low-frequency signals. Therefore, they are easily influenced by external factors. EEG artifact removal is crucial in neuroscience because artifacts have a significant impact on the results of …
BenchmarkingDeep LearningEEGEEG Artifact Removal+1