AI Paper Atlas

Research map / Image generation / Image restoration

Self-supervised Bayesian Deep Learning for Image Recovery with Applications to Compressive Sensing

Tongyao Pang, Yuhui Quan, Hui Ji

ECCV 2020 · Image generation › Image restoration · approach: Diffusion priors for denoising and deblurring · 32 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 random Bayesian weights (vs MLE deterministic weights) (ablation)Self-supervised BNN · Set11 CS (noiseless, ratio 25%)PSNR (dB): 29.43 -> 32.30Improved
add random Bayesian weights (vs MAP deterministic weights) (ablation)Self-supervised BNN · Set11 CS (noiseless, ratio 25%)PSNR (dB): 29.51 -> 32.30Improved
add random Bayesian weights (vs MLE deterministic weights) (ablation)Self-supervised BNN · Set11 CS (noise 10, ratio 25%)PSNR (dB): 27.24 -> 28.67Improved
add random Bayesian weights (vs MAP deterministic weights) (ablation)Self-supervised BNN · Set11 CS (noise 10, ratio 4%)PSNR (dB): 20.25 -> 21.91Improved
add random Bayesian weights (vs MLE deterministic weights) (ablation)Self-supervised BNN · Set11 CS (noiseless, ratio 4%)PSNR (dB): 21.13 -> 23.26Improved
add Gaussian weight prior (MAP vs MLE) to deterministic network (ablation)deterministic network · Set11 CS (noiseless, ratio 4%)PSNR (dB): 21.13 -> 21.08No clear effect
add Gaussian weight prior (MAP vs MLE) to deterministic network (ablation)deterministic network · Set11 CS (noise 10, ratio 25%)PSNR (dB): 27.24 -> 27.18No clear effect
use BNN instead of DIP for CS reconstructionSelf-supervised BNN · Set11 CS (noise 10, ratio 40%)PSNR (dB): 28.87 -> 30.39Improved
use BNN instead of DIP for CS reconstructionSelf-supervised BNN · MRI 2D Gaussian mask (noise 10%)PSNR (dB): 24.41 -> 27.12Improved
use BNN instead of DIP for CS reconstructionSelf-supervised BNN · MRI 1D Gaussian mask (noiseless)PSNR (dB): 31.80 -> 31.38Hurt
use self-supervised BNN instead of supervised ISTA-NetSelf-supervised BNN · Set11 CS (noiseless, ratio 40%)PSNR (dB): 35.97 -> 35.71Hurt
use self-supervised BNN instead of supervised ISTA-NetSelf-supervised BNN · Set11 CS (noise 10, ratio 40%)PSNR (dB): 27.98 -> 30.39Improved

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