Research map / Video / Video segmentation and tracking
Joint optimization for compressive video sensing and reconstruction under hardware constraints
Michitaka Yoshida, Akihiko Torii, Masatoshi Okutomi, Kenta Endo, Yukinobu Sugiyama, Rin-ichiro Taniguchi, Hajime Nagahara
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 jointly optimized exposure pattern instead of handcrafted single-bump pattern | DNN decoder, SBE sensor · Simulated videos (noise variance 0) | PSNR: 29.41 -> 30.05 | Improved |
| Use jointly optimized exposure pattern instead of handcrafted row-column pattern | DNN decoder, RCE sensor · Simulated videos (noise variance 0) | PSNR: 28.51 -> 29.45 | Improved |
| Use optimized pattern instead of random pattern | DNN decoder, unconstrained sensor · Simulated videos (noise variance 0) | PSNR: 29.17 -> 29.99 | Improved |
| Use optimized RCE pattern instead of handcrafted | DNN decoder, RCE sensor · Simulated videos (noise variance 0.01) | PSNR: 26.76 -> 27.46 | Improved |
| Use optimized RCE pattern instead of handcrafted | DNN decoder, RCE sensor · Simulated videos (noise variance 0.05) | PSNR: 19.85 -> 20.22 | Improved |
| Use optimized instead of random pattern under heavy noise | DNN decoder, unconstrained sensor · Simulated videos (noise variance 0.05) | PSNR: 23.08 -> 22.05 | Hurt |
| Use optimized instead of random pattern under heavy noise | GMM decoder, unconstrained sensor · Simulated videos (noise variance 0.05) | PSNR: 22.13 -> 21.25 | Hurt |
| Use optimized SBE pattern instead of handcrafted | GMM decoder, SBE sensor · Simulated videos (noise variance 0) | PSNR: 27.69 -> 29.63 | Improved |
| Use optimized SBE pattern instead of handcrafted | OMP decoder, SBE sensor · Simulated videos (noise variance 0) | PSNR: 24.66 -> 26.22 | Improved |
| Use optimized RCE pattern instead of handcrafted | OMP decoder, RCE sensor · Simulated videos (noise variance 0.05) | PSNR: 17.59 -> 17.42 | Hurt |
| Use DNN decoder instead of OMP with optimized RCE pattern | Optimized RCE pattern · Simulated videos (noise variance 0) | PSNR: 24.22 -> 29.45 | Improved |
| Use DNN decoder instead of GMM with optimized RCE pattern | Optimized RCE pattern · Simulated videos (noise variance 0) | PSNR: 28.82 -> 29.45 | Improved |
Closest papers by meaning
- Sinusoidal Sampling Enhanced Compressive Camera for High Speed Imaging (TPAMI 2019 · similarity 0.85)
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (TPAMI 2021 · similarity 0.85)
- Rank Minimization for Snapshot Compressive Imaging (TPAMI 2018 · similarity 0.85)
- Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.84)
- Sampling Innovation-Based Adaptive Compressive Sensing (CVPR 2025 · similarity 0.83)
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.82)
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.
