AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

FFT-OT: A Fast Algorithm for Optimal Transportation

Na Lei, Xianfeng Gu

ICCV 2021 · Learning theory and algorithms › Optimal transport · approach: Transport map estimation · 10 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
increase grid resolution from 512 to 1kFFT-OT · Buddha surfacespeedup over Su et al.: 39.198 -> 101.450Improved
increase grid resolution from 512 to 1kFFT-OT · Female facespeedup over Su et al.: 52.323 -> 167.834Improved
increase grid resolution from 512 to 1kFFT-OT · David headspeedup over Su et al.: 8.482 -> 17.239Improved
increase grid resolution from 1k to 2kFFT-OT · Buddha surfaceruntime (s): 11.8304 -> 97.8272Hurt
increase grid resolution from 1k to 2kFFT-OT · Brain cortical surfaceruntime (s): 80.9929 -> 705.6193Hurt
replace convex geometric optimization with FFT-OTOT map computation · Buddha surface 1k x 1kruntime (s): 1200.189 -> 11.8304Improved
increase resolution nFFT-OT · Buddha and brain surfacesL2 approximation error: En proportional to 1/n^2Improved

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