AI Paper Atlas

Research map / Image generation / Super-resolution

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

Sachit Menon, Alexandru Damian, Shijia Hu, Nikhil Ravi, Cynthia Rudin

CVPR 2020 · Image generation › Super-resolution · approach: Real-world super-resolution · 541 citations (OpenAlex)

Check 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 PULSE instead of FSRGANFace super-resolution · CelebA HQ, 8×, 128 × 128MOS: 2.92 -> 3.60Improved
Use PULSE instead of FSRNetFace super-resolution · CelebA HQ, 8×, 128 × 128MOS: 2.77 -> 3.60Improved
Use PULSE instead of bicubic upscalingFace super-resolution · CelebA HQ, 8×, 128 × 128MOS: 1.34 -> 3.60Improved
Use PULSE instead of bicubic upscalingFace super-resolution · CelebA HQ, 64×, 1024 × 1024NIQE: 7.06 -> 2.47Improved
Use PULSE instead of nearest-neighbor upscalingFace super-resolution · CelebA HQ, 64×, 1024 × 1024NIQE: 12.48 -> 2.47Improved
Change the hypersphere radius used for latent search (ablation)PULSE with StyleGAN-FFHQ · FairFace, ×64success rateNo clear effect
Relax StyleGAN's constraint by allowing its 18 latent vectors to vary while encouraging them to be approximately equal (ablation)PULSE with StyleGAN-FFHQ · Face super-resolutionrealismImproved
Loosen StyleGAN's latent-space constraints further (ablation)PULSE with StyleGAN-FFHQ · Face super-resolutionrealismHurt
Use PULSE with bicubic downscaling as a stand-in when the true degradation includes noise or blurPULSE · Unknown degradation operatorsdownscaling correctnessImproved

Later papers that compared with this method

10 later accepted papers report PULSE as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

2 more not listed.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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