AI Paper Atlas

Research map / Image generation / Image restoration

ptwt - The PyTorch Wavelet Toolbox

Moritz Wolter, Felix Blanke, Jochen Garcke, Charles Tapley Hoyt

JMLR 2024 · Image generation › Image restoration · approach: Inverse imaging with learned priors

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
run DWT-2D separable on GPU with ptwt instead of Cotter (2022)ptwt · DWT-2D separablerun-time: 0.01474 -> 0.00995Improved
move ptwt DWT-1D from CPU to GPU (ablation)ptwt · DWT-1Drun-time: 0.40286 -> 0.00887Improved
add jit to ptwt DWT-1D on GPU (ablation)ptwt · DWT-1Drun-time: 0.00887 -> 0.00439Improved
add jit to ptwt DWT-3D on GPU (ablation)ptwt · DWT-3Drun-time: 0.08047 -> 0.08096No clear effect
use ptwt instead of PyWavelets on CPU for DWT-1Dptwt · DWT-1Drun-time: 0.40286 vs 0.25841Hurt
use ptwt instead of PyWavelets on CPU for DWT-2Dptwt · DWT-2Drun-time: 0.54936 -> 0.17453Improved
use ptwt instead of PyWavelets on CPU for CWTptwt · CWTrun-time: 0.94439 -> 0.16029Improved
move ptwt CWT from CPU to GPU and add jit (ablation)ptwt · CWTrun-time: 0.16029 -> 0.01957 -> 0.01566Improved

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