Research map / Image generation / Image restoration
Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
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 an untrained deep network prior instead of a DCT sparse prior | Net-GD and Net-PGD · Compressive sensing, MNIST and CelebA | nMSE | Helped |
| Use an untrained deep network prior instead of a DCT sparse prior | Net-GD and Net-PGD · Compressive phase retrieval, MNIST and CelebA | nMSE | Helped |
| Use uniform random initialization of network weights | Net-PGD · Compressive phase retrieval, MNIST and CelebA | initialization distance δ_i: 0.914, 0.942, 0.913, 0.915 | Helped |
| Use Net-PGD instead of Net-GD | Compressive sensing reconstruction · MNIST examples | average running time: 5.86s -> 5.46s | Helped |
| Use Net-PGD instead of Net-GD | Compressive phase retrieval reconstruction · MNIST examples | average running time: 25.59s -> 28.46s | Hurt |
Closest papers by meaning
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.91)
- A Restoration Network as an Implicit Prior (ICLR 2024 · similarity 0.90)
- Unrolled denoising networks provably learn to perform optimal Bayesian inference (NeurIPS 2024 · similarity 0.88)
- Using Powerful Prior Knowledge of Diffusion Model in Deep Unfolding Networks for Image Compressive Sensing (CVPR 2025 · similarity 0.88)
- NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems (NeurIPS 2025 · similarity 0.88)
- UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights (NeurIPS 2025 · similarity 0.88)
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.