{"url":"/method/adaptive-instance-normalization","slug":"adaptive-instance-normalization","name":"Adaptive Instance Normalization","full_name":"Adaptive Instance Normalization","full_name_withheld":false,"description_markdown":"**Adaptive Instance Normalization** is a normalization method that aligns the mean and variance of the content features with those of the style features. \r\n\r\n[Instance Normalization](https://paperswithcode.com/method/instance-normalization) normalizes the input to a single style specified by the affine parameters. Adaptive Instance Normaliation is an extension. In AdaIN, we receive a content input $x$ and a style input $y$, and we simply align the channel-wise mean and variance of $x$ to match those of $y$. Unlike [Batch Normalization](https://paperswithcode.com/method/batch-normalization), Instance Normalization or [Conditional Instance Normalization](https://paperswithcode.com/method/conditional-instance-normalization), AdaIN has no learnable affine parameters. Instead, it adaptively computes the affine parameters from the style input:\r\n\r\n$$\r\n\\textrm{AdaIN}(x, y)= \\sigma(y)\\left(\\frac{x-\\mu(x)}{\\sigma(x)}\\right)+\\mu(y)\r\n$$","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"http://arxiv.org/abs/1703.06868v2","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/naoto0804/pytorch-AdaIN/blob/5eb7f9f1091cdb98bf76d775a50388805a1f0cca/function.py#L15","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Normalization","url":"/methods/category/normalization","pwc_aliases":[]}],"n_papers_tagged":429,"archive_num_papers":null,"papers_newest_first":[{"paper":"/paper/2506-08357","title":"MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion","date":"2025-06-10","arxiv_id":"2506.08357","n_code_links":1,"syntology":null},{"paper":null,"title":"Improving Heart Rejection Detection in XPCI Images Using Synthetic Data Augmentation","date":"2025-05-26","arxiv_id":"2505.19746","n_code_links":0,"syntology":null},{"paper":"/paper/style-transfer-with-diffusion-models-for","title":"Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation","date":"2025-05-22","arxiv_id":"2505.16360","n_code_links":1,"syntology":null},{"paper":null,"title":"ToonifyGB: StyleGAN-based Gaussian Blendshapes for 3D Stylized Head Avatars","date":"2025-05-15","arxiv_id":"2505.10072","n_code_links":0,"syntology":null},{"paper":null,"title":"PIDiff: Image Customization for Personalized Identities with Diffusion Models","date":"2025-05-08","arxiv_id":"2505.05081","n_code_links":0,"syntology":null},{"paper":"/paper/revealing-unintentional-information-leakage","title":"Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations","date":"2025-03-12","arxiv_id":"2503.09306","n_code_links":1,"syntology":null},{"paper":null,"title":"A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation","date":"2025-01-23","arxiv_id":"2501.13718","n_code_links":0,"syntology":null},{"paper":null,"title":"Detection of AI Deepfake and Fraud in Online Payments Using GAN-Based Models","date":"2025-01-13","arxiv_id":"2501.07033","n_code_links":0,"syntology":null},{"paper":null,"title":"iFADIT: Invertible Face Anonymization via Disentangled Identity Transform","date":"2025-01-08","arxiv_id":"2501.04390","n_code_links":0,"syntology":null},{"paper":null,"title":"ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial Training","date":"2025-01-08","arxiv_id":"2501.04416","n_code_links":0,"syntology":null},{"paper":null,"title":"LLM-driven Multimodal and Multi-Identity Listening Head Generation","date":"2025-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"title":"StyleAutoEncoder for manipulating image attributes using pre-trained StyleGAN","date":"2024-12-28","arxiv_id":"2412.20164","n_code_links":0,"syntology":null},{"paper":null,"title":"NijiGAN: Transform What You See into Anime with Contrastive Semi-Supervised Learning and Neural Ordinary Differential Equations","date":"2024-12-27","arxiv_id":"2412.19455","n_code_links":0,"syntology":null},{"paper":"/paper/singular-value-scaling-efficient-generative","title":"Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement","date":"2024-12-23","arxiv_id":"2412.17387","n_code_links":1,"syntology":null},{"paper":null,"title":"StyleDiT: A Unified Framework for Diverse Child and Partner Faces Synthesis with Style Latent Diffusion Transformer","date":"2024-12-14","arxiv_id":"2412.10785","n_code_links":0,"syntology":null},{"paper":null,"title":"StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements","date":"2024-12-11","arxiv_id":"2412.08503","n_code_links":0,"syntology":null},{"paper":null,"title":"D-LORD for Motion Stylization","date":"2024-12-05","arxiv_id":"2412.04097","n_code_links":0,"syntology":null},{"paper":null,"title":"Z-STAR+: A Zero-shot Style Transfer Method via Adjusting Style Distribution","date":"2024-11-28","arxiv_id":"2411.19231","n_code_links":0,"syntology":null},{"paper":null,"title":"Editable-DeepSC: Reliable Cross-Modal Semantic Communications for Facial Editing","date":"2024-11-24","arxiv_id":"2411.15702","n_code_links":0,"syntology":null},{"paper":"/paper/hypergan-clip-a-unified-framework-for-domain","title":"HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation","date":"2024-11-19","arxiv_id":"2411.12832","n_code_links":1,"syntology":null},{"paper":null,"title":"HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion","date":"2024-10-29","arxiv_id":"2410.21789","n_code_links":0,"syntology":null},{"paper":"/paper/medical-imaging-complexity-and-its-effects-on","title":"Medical Imaging Complexity and its Effects on GAN Performance","date":"2024-10-23","arxiv_id":"2410.17959","n_code_links":1,"syntology":null},{"paper":"/paper/3d-gantex-3d-face-reconstruction-with","title":"3D-GANTex: 3D Face Reconstruction with StyleGAN3-based Multi-View Images and 3DDFA based Mesh Generation","date":"2024-10-21","arxiv_id":"2410.16009","n_code_links":1,"syntology":null},{"paper":null,"title":"Detecting Unforeseen Data Properties with Diffusion Autoencoder Embeddings using Spine MRI data","date":"2024-10-14","arxiv_id":"2410.10220","n_code_links":0,"syntology":null},{"paper":null,"title":"Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification","date":"2024-10-11","arxiv_id":"2410.08466","n_code_links":0,"syntology":null},{"paper":null,"title":"RefineStyle: Dynamic Convolution Refinement for StyleGAN","date":"2024-10-08","arxiv_id":"2410.06104","n_code_links":0,"syntology":null},{"paper":null,"title":"Harnessing the Latent Diffusion Model for Training-Free Image Style Transfer","date":"2024-10-02","arxiv_id":"2410.01366","n_code_links":0,"syntology":null},{"paper":"/paper/ossa-unsupervised-one-shot-style-adaptation","title":"OSSA: Unsupervised One-Shot Style Adaptation","date":"2024-10-01","arxiv_id":"2410.00900","n_code_links":1,"syntology":null},{"paper":"/paper/mm2latent-text-to-facial-image-generation-and","title":"MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance","date":"2024-09-17","arxiv_id":"2409.11010","n_code_links":1,"syntology":null},{"paper":null,"title":"Controllable retinal image synthesis using conditional StyleGAN and latent space manipulation for improved diagnosis and grading of diabetic retinopathy","date":"2024-09-11","arxiv_id":"2409.07422","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":88},{"task":"/task/attribute","name":"Attribute","papers":45},{"task":"/task/disentanglement","name":"Disentanglement","papers":42},{"task":"/task/style-transfer","name":"Style Transfer","papers":33},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":24},{"task":"/task/image-manipulation","name":"Image Manipulation","papers":22},{"task":"/task/face-generation","name":"Face Generation","papers":21},{"task":"/task/decoder","name":"Decoder","papers":18},{"task":"/task/face-recognition","name":"Face Recognition","papers":18},{"task":null,"name":"Generative Adversarial Network","papers":18},{"task":"/task/translation","name":"Translation","papers":17},{"task":"/task/diversity","name":"Diversity","papers":16},{"task":"/task/domain-adaptation","name":"Domain Adaptation","papers":16},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":15},{"task":"/task/face-swapping","name":"Face Swapping","papers":15},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":13},{"task":"/task/super-resolution","name":"Super-Resolution","papers":12},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":11},{"task":"/task/video-generation","name":"Video Generation","papers":10},{"task":"/task/denoising","name":"Denoising","papers":9}],"tasks_shown":20,"n_tasks":229,"usage_by_year":[{"year":"2017","papers":2},{"year":"2018","papers":3},{"year":"2019","papers":17},{"year":"2020","papers":52},{"year":"2021","papers":79},{"year":"2022","papers":95},{"year":"2023","papers":106},{"year":"2024","papers":64},{"year":"2025","papers":11}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/adaptive-instance-normalization"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}