Research map / Video / Video segmentation and tracking
A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging
Miao Cao, Lishun Wang, Huan Wang, Xin Yuan
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 |
|---|---|---|---|
| add shifted Transformer branch (learnable shift on query and key) to 4-bit baseline (ablation) | Q-SCI 4-bit EfficientSCI-S · Video SCI simulated | PSNR (dB): 31.40 -> 31.93 | Improved |
| add high-quality feature extraction module (8-bit 1x1x1 shortcut convs) (ablation) | Q-SCI 4-bit EfficientSCI-S · Video SCI simulated | PSNR (dB): 31.93 -> 34.28 | Improved |
| add precise video reconstruction module (8-bit shortcut convs) (ablation) | Q-SCI 4-bit EfficientSCI-S · Video SCI simulated | PSNR (dB): 34.28 -> 34.71 | Improved |
| add feature extraction module to 4-bit STFormer-S (ablation) | STFormer-S 4-bit · Video SCI simulated | PSNR (dB): 30.03 -> 33.26 | Improved |
| add video reconstruction module to 4-bit STFormer-S (ablation) | STFormer-S 4-bit · Video SCI simulated | PSNR (dB): 33.26 -> 33.51 | Improved |
| keep feature extraction module at 8-bit rather than 4-bit (ablation) | 8-bit EfficientSCI-S baseline · Video SCI simulated | PSNR (dB): 33.01 -> 35.23 | Improved |
| keep video reconstruction module at 8-bit rather than 4-bit (ablation) | 8-bit EfficientSCI-S baseline · Video SCI simulated | PSNR (dB): 34.74 -> 35.23 | Improved |
| use Q-SCI instead of Q-ViT at 8-bit | EfficientSCI-S · Video SCI simulated | PSNR (dB): 35.17 -> 35.57 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- BIRNAT — BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging (ECCV 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (TPAMI 2021 · similarity 0.91)
- EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging (CVPR 2023 · similarity 0.91)
- Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging (CVPR 2020 · similarity 0.89)
- Memory-Efficient Network for Large-Scale Video Compressive Sensing (CVPR 2021 · similarity 0.89)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.88)
- bit2bit: 1-bit quanta video reconstruction via self-supervised photon prediction (NeurIPS 2024 · similarity 0.87)
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.
