Research map / Learning theory and algorithms / Matrix and tensor methods
Unsupervised Learning From Incomplete Measurements for Inverse Problems
Julián Tachella, Dongdong Chen, Mike Davies
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use MOI loss instead of AmbientGAN | unsupervised inpainting · CelebA inpainting | PSNR (dB): 29.57 -> 34.05 | Improved |
| MOI instead of measurement splitting, denoiser architecture | unsupervised MRI reconstruction · FastMRI 4x | PSNR (dB): 28.72 -> 29.51 | Improved |
| MOI instead of measurement splitting, unrolled architecture | unsupervised MRI reconstruction · FastMRI 4x | PSNR (dB): 29.47 -> 31.39 | Improved |
| use unrolled network instead of denoiser network (ablation) | MOI · FastMRI 4x | PSNR (dB): 29.51 -> 31.39 | Improved |
| train measurement splitting on full measurements instead of reduced A_{g,1} (ablation) | measurement splitting, denoiser · FastMRI 4x | PSNR (dB): 28.72 -> 27.3 | Hurt |
| use U-Net instead of DCGAN as AmbientGAN generator (ablation) | AmbientGAN · CelebA inpainting | PSNR | Hurt |
| fewer measurements/operators than the bound m > k + n/G (ablation) | MOI on MNIST · MNIST CS (G=1..40, m=50..400) | PSNR improvement over pseudo-inverse | Hurt |
Closest papers by meaning
- Sensing Theorems for Unsupervised Learning in Linear Inverse Problems (JMLR 2023 · similarity 0.93)
- NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems (NeurIPS 2025 · similarity 0.87)
- A Diffusion Model with State Estimation for Degradation-Blind Inverse Imaging (AAAI 2024 · similarity 0.85)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.85)
- FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems (CVPR 2025 · similarity 0.85)
- Learning Single Index Models with Diffusion Priors (ICML 2025 · similarity 0.85)
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.
