paper-with-me

Papers

Parallel Multiscale Autoregressive Density Estimation

2017-03-10 · ICML 2017 8 · Scott Reed, Aäron van den Oord, Nal Kalchbrenner, Sergio Gómez Colmenarejo, Ziyu Wang, Dan Belov, Nando de Freitas

PixelCNN achieves state-of-the-art results in density estimation for natural images. Although training is fast, inference is costly, requiring one network evaluation per pixel; O(N) for N pixels. This can be sped up by caching activations, but still involves generating each pixel sequentially. In this work, we propose a parallelized PixelCNN that allows more efficient inference by modeling certain pixel groups as conditionally independent. Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images. We evaluate the model on class-conditional image generation, text-to-image synthesis, and action-conditional video generation, showing that our model achieves the best results among non-pixel-autoregressive density models that allow efficient sampling.

📄 PDF Abstract BibTeX arXiv:1703.03664

Code (0)

등록된 구현이 없습니다.

Tasks

Conditional Image GenerationDensity EstimationImage CompressionImage GenerationVideo Generation

Methods 이 논문이 사용한 방법론

PixelCNN A PixelCNN is a generative model that uses autoregressive connections to model images pixel by pixel, decomposing the joint image distribution as a product of conditionals.…

Similar Papers 제목 키워드 기반

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

2023-05-12 · NeurIPS 2023 11 · Lili Yu, Dániel Simig, Colin Flaherty, Armen Aghajanyan 외

Autoregressive transformers are spectacular models for short sequences but scale poorly to long sequences such as high-resolution images, podcasts, code, or books. We proposed Megabyte, a multi-scale decoder architecture…

DecoderDensity EstimationLanguage ModelingLanguage Modelling

Progressive Checkerboards for Autoregressive Multiscale Image Generation

2026-02-03 · David Eigen arxiv

A key challenge in autoregressive image generation is to efficiently sample independent locations in parallel, while still modeling mutual dependencies with serial conditioning. Some recent works have addressed this by c…

Image Generation

Generative Model with Dynamic Linear Flow

2019-05-08 · Huadong Liao, JiaWei He, Kunxian Shu

Flow-based generative models are a family of exact log-likelihood models with tractable sampling and latent-variable inference, hence conceptually attractive for modeling complex distributions. However, flow-based models…

Density Estimationmodel

PixelPyramids: Exact Inference Models from Lossless Image Pyramids

2021-10-17 · ICCV 2021 10 · Shweta Mahajan, Stefan Roth

Autoregressive models are a class of exact inference approaches with highly flexible functional forms, yielding state-of-the-art density estimates for natural images. Yet, the sequential ordering on the dimensions makes …

Density Estimation

Masked Autoregressive Flow for Density Estimation

2017-05-19 · NeurIPS 2017 12 · George Papamakarios, Theo Pavlakou, Iain Murray

Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses …

Density Estimation