{"url":"/method/pixelrnn","slug":"pixelrnn","name":"PixelRNN","full_name":"Pixel Recurrent Neural Network","full_name_withheld":false,"description_markdown":"**PixelRNNs** are generative neural networks that sequentially predicts the pixels in an image along the two spatial dimensions. They model the discrete probability of the raw pixel values and encode the complete set of dependencies in the image. Variants include the Row [LSTM](https://paperswithcode.com/method/lstm) and the Diagonal [BiLSTM](https://paperswithcode.com/method/bilstm), that scale more easily to larger datasets. Pixel values are treated as discrete random variables by using a [softmax](https://paperswithcode.com/method/softmax) layer in the conditional distributions. Masked convolutions are employed to allow PixelRNNs to model full dependencies between the color channels.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Pixel Recurrent Neural Networks","paper":"/paper/pixel-recurrent-neural-networks","first_author":"Aaron van den Oord","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pixel-recurrent-neural-networks"},"source":{"url":"http://arxiv.org/abs/1601.06759v3","title":"Pixel Recurrent Neural Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/carpedm20/pixel-rnn-tensorflow","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Likelihood-Based Generative Models","url":"/methods/category/likelihood-based-generative-models","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":4,"archive_num_papers":4,"papers_newest_first":[{"paper":null,"title":"PixelRNN: In-pixel Recurrent Neural Networks for End-to-end-optimized Perception with Neural Sensors","date":"2023-04-11","arxiv_id":"2304.05440","n_code_links":0,"syntology":null},{"paper":"/paper/full-resolution-image-compression-with","title":"Full Resolution Image Compression with Recurrent Neural Networks","date":"2016-08-18","arxiv_id":"1608.05148","n_code_links":7,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":0}},{"paper":"/paper/conditional-image-generation-with-pixelcnn","title":"Conditional Image Generation with PixelCNN Decoders","date":"2016-06-16","arxiv_id":"1606.05328","n_code_links":14,"syntology":{"ran":4,"of":14,"unverified":10,"pointer_only":3}},{"paper":"/paper/pixel-recurrent-neural-networks","title":"Pixel Recurrent Neural Networks","date":"2016-01-25","arxiv_id":"1601.06759","n_code_links":20,"syntology":{"ran":19,"of":29,"unverified":10,"pointer_only":18}}],"papers_shown":4,"tasks":[{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/image-generation","name":"Image Generation","papers":2},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":1},{"task":"/task/density-estimation","name":"Density Estimation","papers":1},{"task":"/task/descriptive","name":"Descriptive","papers":1},{"task":"/task/gesture-recognition","name":"Gesture Recognition","papers":1},{"task":"/task/hand-gesture-recognition","name":"Hand Gesture Recognition","papers":1},{"task":"/task/hand-gesture-recognition-1","name":"Hand-Gesture Recognition","papers":1},{"task":"/task/image-compression","name":"Image Compression","papers":1},{"task":"/task/lip-reading","name":"Lip Reading","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2016","papers":3},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/pixelrnn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}