Research map / Video / Video segmentation and tracking
Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network
Ruiying Lu, Bo Chen, Guanliang Liu, Ziheng Cheng, Mu Qiao, 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 diversity amplifier (ablation) | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | PSNR (dB): 24.55 -> 25.12 | Improved |
| use dual-branch separator instead of single branch (ablation) | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | PSNR (dB): 24.83 -> 25.12 | Improved |
| add refine net (ablation) | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | PSNR (dB): 24.01 -> 25.12 | Improved |
| add bidirectional optical flow (ablation) | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | PSNR (dB): 24.42 -> 25.12 | Improved |
| add joint training of FlowNet (ablation) | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | PSNR (dB): 24.87 -> 25.12 | Improved |
| use bidirectional recurrent refining network instead of OFaNet's condensed one (ablation) | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | PSNR (dB): 25.01 -> 25.12 | No clear effect |
| OFaNet vs DeSCI at B=14 | OFaNet · Dual-view SCI (B=14) | PSNR (dB): 21.73 -> 24.25 | Improved |
| OFaNet vs DeSCI under noise sigma=0.2 | OFaNet · Dual-view SCI (noise) | PSNR (dB): 5.35 -> 14.83 | Improved |
| OFaNet vs DeSCI inference time | OFaNet · Dual-view SCI simulation (6 datasets avg, B=10) | running time (s): 21600.4 -> 0.4893 | Improved |
| OFaNet vs BIRNAT on single-view | OFaNet · Single-view SCI simulation (6 datasets avg) | PSNR (dB): 33.31 -> 32.88 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- BIRNAT — BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging (ECCV 2020) · better on 2 of 4 shared results
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
- Recurrent Neural Networks for Snapshot Compressive Imaging (TPAMI 2022 · similarity 0.91)
- BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging (ECCV 2020 · similarity 0.90)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.90)
- Deep Optics for Video Snapshot Compressive Imaging (ICCV 2023 · similarity 0.89)
- Memory-Efficient Network for Large-Scale Video Compressive Sensing (CVPR 2021 · similarity 0.89)
- Dual Prior Unfolding for Snapshot Compressive Imaging (CVPR 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.
