AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Neural FFTs for Universal Texture Image Synthesis

Morteza Mardani, Guilin Liu, Aysegul Dundar, Shiqiu Liu, Andrew Tao, Bryan Catanzaro

NeurIPS 2020 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 12 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
add FFT-domain upsampling of features (vs CNN on features without FFT) (ablation)Neural FFT · Texture test set (128->256, 200 images)FID: 147.6 -> 71.82Improved
add FFT-domain upsampling of features (ablation)Neural FFT · Texture test set (128->256, 200 images)SSIM: 0.29 -> 0.48Improved
upsample in feature space instead of end-to-end FFT of the image (ablation)Neural FFT · Texture test set (128->256, 200 images)FID: 126.3 -> 71.82Improved
upsample in feature space instead of end-to-end FFT of the image (ablation)Neural FFT · Texture test set (128->256, 200 images)SSIM: 0.28 -> 0.48Improved
add deformable convolutions to the FFT upsampler (ablation)Neural FFT · Texture test set (128->256, 200 images)FID: 76.00 -> 71.82Improved
add deformable convolutions to the FFT upsampler (ablation)Neural FFT · Texture test set (128->256, 200 images)SSIM: 0.46 -> 0.48Improved
add deformable convolutions to the FFT upsampler (ablation)Neural FFT · Texture test set (128->256, 200 images)LPIPS: 0.27 -> 0.25Improved
Neural FFT vs Texture CNN (which uses full ground-truth texture)Neural FFT · Texture test set (128->256, 200 images)FID: 68.97 -> 71.82Hurt
Neural FFT vs self-tuning optimization baselineNeural FFT · Texture test set (128->256, 200 images)human preference / runtime: PS 58; 45 ms vs 140 sImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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