Research map / 3D vision / Depth and stereo
Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems
Edwin Vargas, Julien N. P. Martel, Gordon Wetzstein, Henry Arguello
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 |
|---|---|---|---|
| replace ADMM decoder with a U-Net decoder (ablation) | CASSI codification · ICVL 1 compressive spectral imaging | PSNR: 27.40 -> 29.66 | Improved |
| use TMCA codification with random codes instead of CASSI codification, same U-Net decoder | U-Net decoder · ICVL 1 compressive spectral imaging | PSNR: 29.66 -> 31.39 | Improved |
| learn TMCA codes end-to-end instead of random codes (ablation) | TMCA · ICVL 1 compressive spectral imaging | PSNR: 31.39 -> 32.72 | Improved |
| learn TMCA codes end-to-end instead of random codes (ablation) | TMCA · ICVL 1 compressive spectral imaging | SAM: 13.01 -> 11.92 | Improved |
| use TMCA with random codes instead of CLFP deep net codification | deep net decoder · Aggregated Lytro compressive light field | PSNR: 32.43 -> 34.03 | Improved |
| learn TMCA codes instead of random codes (ablation) | TMCA · Aggregated Lytro compressive light field | PSNR: 34.03 -> 34.89 | Improved |
| learn TMCA codes instead of random codes (ablation) | TMCA · Aggregated Lytro compressive light field | SSIM: 0.93 -> 0.94 | Improved |
| replace dictionary-learning decoder with deep net decoder (ablation) | CLFP codification · Aggregated Lytro compressive light field | PSNR: 30.06 -> 32.43 | Improved |
| increase shutter time slots from K=1 to K=8 (ablation) | measurement matrix conditioning · light field and spectral imaging | eigenvalue spread | Improved |
Closest papers by meaning
- Snapshot Compressive ToF+Spectral Imaging via Optimized Color-Coded Apertures (TPAMI 2019 · similarity 0.91)
- Adaptive Nonlocal Sparse Representation for Dual-Camera Compressive Hyperspectral Imaging (TPAMI 2016 · similarity 0.88)
- Effective Snapshot Compressive-Spectral Imaging via Deep Denoising and Total Variation Priors (CVPR 2021 · similarity 0.88)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · similarity 0.88)
- Spectral Compressive Imaging via Chromaticity-Intensity Decomposition (NeurIPS 2025 · similarity 0.86)
- Passive Snapshot Coded Aperture Dual-Pixel RGB-D Imaging (CVPR 2024 · similarity 0.86)
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.
