English

PixelPyramids: Exact Inference Models from Lossless Image Pyramids

Computer Vision and Pattern Recognition 2021-10-19 v1 Machine Learning Image and Video Processing

Abstract

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 these models computationally expensive and limits their applicability to low-resolution imagery. In this work, we propose Pixel-Pyramids, a block-autoregressive approach employing a lossless pyramid decomposition with scale-specific representations to encode the joint distribution of image pixels. Crucially, it affords a sparser dependency structure compared to fully autoregressive approaches. Our PixelPyramids yield state-of-the-art results for density estimation on various image datasets, especially for high-resolution data. For CelebA-HQ 1024 x 1024, we observe that the density estimates (in terms of bits/dim) are improved to ~44% of the baseline despite sampling speeds superior even to easily parallelizable flow-based models.

Keywords

Cite

@article{arxiv.2110.08787,
  title  = {PixelPyramids: Exact Inference Models from Lossless Image Pyramids},
  author = {Shweta Mahajan and Stefan Roth},
  journal= {arXiv preprint arXiv:2110.08787},
  year   = {2021}
}

Comments

To appear at ICCV 2021

R2 v1 2026-06-24T06:57:12.483Z