Research map / Video / Video segmentation and tracking
EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging
Lishun Wang, Miao Cao, 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 dense connections within ResDNet at GN 4 (ablation) | EfficientSCI · Six grayscale benchmark datasets | PSNR: 35.02 -> 36.48 | Improved |
| Replace SCB with Swin Transformer (ablation) | EfficientSCI CFormer · Six grayscale benchmark datasets | PSNR: 35.51 -> 34.99 | Hurt |
| Replace SCB and TSAB with two stacked 3D convolutions (ablation) | EfficientSCI CFormer · Six grayscale benchmark datasets | PSNR: 35.51 -> 34.93 | Hurt |
| Increase the number of channels and blocks (ablation) | EfficientSCI · Six grayscale benchmark datasets | PSNR: 34.22 -> 35.51 -> 36.48 -> 36.92 | Improved |
| Remove regularization layers (ablation) | EfficientSCI CFormer · Video SCI reconstruction | reconstruction quality | No clear effect |
Closest papers by meaning
- Memory-Efficient Network for Large-Scale Video Compressive Sensing (CVPR 2021 · similarity 0.93)
- MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing (CVPR 2021 · similarity 0.92)
- A Simple Low-bit Quantization Framework for Video Snapshot Compressive Imaging (ECCV 2024 · similarity 0.91)
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (TPAMI 2021 · similarity 0.91)
- Tensor FISTA-Net for Real-Time Snapshot Compressive Imaging (AAAI 2020 · similarity 0.90)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.88)
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.
