Research map / Image generation / Image restoration
Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use DivNoising instead of Noise2Void | BSD68 with Gaussian noise σ=25 · BSD68 | PSNR: 27.71 -> 27.45 | Hurt |
| Use DivNoising instead of Deep Image Prior | DenoiSeg Flywing · DenoiSeg Flywing | PSNR: 24.67±0.050 -> 25.02±0.024 | Helped |
| Set the KL-loss weight β to 1 rather than β above or below 1 (ablation) | DivNoising on DenoiSeg Flywing · DenoiSeg Flywing | MMSE PSNR | Helped |
| Increase the KL-loss weight β above 1 (ablation) | DivNoising on DenoiSeg Flywing · DenoiSeg Flywing | standard deviation PSNR | Helped |
| Increase the noise level (ablation) | DivNoising on DenoiSeg Flywing · DenoiSeg Flywing | standard deviation PSNR | Helped |
| Use multiple diverse denoising samples with Consensus (Avg) rather than only the MMSE estimate | DivNoising cell segmentation pipeline · DenoiSeg Flywing | instance segmentation quality | Helped |
Closest papers by meaning
- Interpretable Unsupervised Diversity Denoising and Artefact Removal (ICLR 2022 · similarity 0.93)
- Universal Denoising Networks : A Novel CNN Architecture for Image Denoising (CVPR 2018 · similarity 0.90)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.89)
- SeNM-VAE: Semi-Supervised Noise Modeling with Hierarchical Variational Autoencoder (CVPR 2024 · similarity 0.88)
- Diffusion Priors for Variational Likelihood Estimation and Image Denoising (NeurIPS 2024 · similarity 0.87)
- Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise (NeurIPS 2024 · similarity 0.87)
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.