Research map / Video / Video segmentation and tracking
Memory-Efficient Network for Large-Scale Video Compressive Sensing
Check 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 the RevSCI-net reconstruction model | video SCI reconstruction · Six grayscale datasets (average) | PSNR (dB): 33.31 -> 33.92 | Helped |
| Use the RevSCI-net reconstruction model | video SCI reconstruction · Messi | PSNR (dB): 21.54 -> 24.35 | Helped |
| Use the RevSCI-net reconstruction model | video SCI reconstruction · Hummingbird | PSNR (dB): 24.13 -> 31.97 | Helped |
| Increase the number of reversible blocks from 18 to 28 (ablation) | RevSCI-net with 2 groups · Six grayscale test sets (average) | PSNR: 33.11 -> 33.34 | Helped |
| Increase the number of reversible blocks from 28 to 50 (ablation) | RevSCI-net with 2 groups · Six grayscale test sets (average) | PSNR: 33.34 -> 33.62 | Helped |
| Increase the number of groups from 2 to 4 (ablation) | RevSCI-net with 50 reversible blocks · Six grayscale test sets (average) | PSNR: 33.62 -> 33.76 | Helped |
| Increase the number of groups from 4 to 8 (ablation) | RevSCI-net with 50 reversible blocks · Six grayscale test sets (average) | PSNR: 33.76 -> 33.84 | Helped |
| Increase the number of reversible blocks from 18 to 50 (ablation) | RevSCI-net with 2 groups · Six grayscale test sets (average) | SSIM: 0.947 -> 0.954 | Helped |
| Increase the number of groups from 2 to 8 (ablation) | RevSCI-net with 50 reversible blocks · Six grayscale test sets (average) | SSIM: 0.954 -> 0.956 | Helped |
Closest papers by meaning
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.91)
- Block Image Compressive Sensing with Local and Global Information Interaction (AAAI 2024 · similarity 0.86)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.86)
- Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging (NeurIPS 2024 · similarity 0.86)
- SCINeRF: Neural Radiance Fields from a Snapshot Compressive Image (CVPR 2024 · similarity 0.86)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 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.