AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

PixelPyramids: Exact Inference Models From Lossless Image Pyramids

Shweta Mahajan, Stefan Roth

ICCV 2021 · Image generation › Fast diffusion sampling · approach: Distributional control of diffusion · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use modulo-difference fine components in the pyramid instead of a regular image pyramid (ablation)PixelPyramids · CelebA 256x256bits/dim: 0.76 -> 0.61Improved
add the partial autoregressive structure (Conv-LSTM via squeeze operations) (ablation)PixelPyramids · CelebA 256x256bits/dim: 0.83 -> 0.61Improved
increase n_squeeze from 0 to 1 (ablation)PixelPyramids · CelebA 256x256bits/dim: 0.83 -> 0.62Improved
increase n_squeeze from 1 to 2 (ablation)PixelPyramids · CelebA 256x256bits/dim: 0.62 -> 0.61Improved
increase n_squeeze from 2 to 3 (ablation)PixelPyramids · CelebA 256x256bits/dim: 0.61 -> 0.61No clear effect
replace Haar wavelet scale-space flow with Paired Pyramid block-autoregressive modelWaveletFlow · CelebA-HQ 1024x1024 (8-bit)bits/dim: 1.34 -> 0.58Improved
use PixelPyramids instead of Glowflow baselines · CelebA-HQ 256x256 (5-bit)bits/dim: 1.03 -> 0.61Improved
use PixelPyramids instead of MaCoWflow baselines · CelebA-HQ 256x256 (5-bit)bits/dim: 0.67 -> 0.61Improved
use PixelPyramids instead of WaveletFlowWaveletFlow · CelebA-HQ 256x256 (5-bit)bits/dim: 0.94 -> 0.61Improved
use PixelPyramids instead of fully autoregressive SPNSPN · ImageNet 128x128 (8-bit)bits/dim: 3.08 -> 3.40Hurt
use PixelPyramids instead of ParallelWaveletParallelWavelet · ImageNet 128x128 (8-bit)bits/dim: 3.55 -> 3.40Improved
use PixelPyramids instead of PixelCNN++ on low-resolution dataPixelCNN++ · CIFAR10 32x32 (8-bit)bits/dim: 2.92 -> 3.19Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy