Research map / Video / Video segmentation and tracking
Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing
Ruiying Lu, Ziheng Cheng, Bo Chen, 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 dynamic walk (DW) sampling (ablation) | MadyGraph · grayscale simulation | PSNR: 36.57 -> 37.08 | Improved |
| add cross-scale (CS) node sampling (ablation) | MadyGraph + DW · grayscale simulation | PSNR: 37.08 -> 37.21 | Improved |
| add motion-aware (MA) information (ablation) | MadyGraph + DW + CS · grayscale simulation | PSNR: 37.21 -> 37.30 | Improved |
| add global knowledge (GK) integration (ablation) | MadyGraph + DW + CS + MA · grayscale simulation | PSNR: 37.30 -> 37.41 | Improved |
| replace fixed-stride sampling with dynamic graph sampling (ablation) | MadyGraph · grayscale simulation | PSNR: 36.57 -> 37.41 | Improved |
| replace self-attention sampling with dynamic graph sampling (ablation) | MadyGraph · grayscale simulation | PSNR: 37.11 -> 37.41 | Improved |
| replace entropy-based sampling with dynamic graph sampling (ablation) | MadyGraph · grayscale simulation | PSNR: 36.94 -> 37.41 | Improved |
| append the graph module to GAP-TV | GAP-TV · grayscale simulation | PSNR: 26.79 -> 29.50 | Improved |
| append the graph module to DeSCI | DeSCI · grayscale simulation | PSNR: 32.72 -> 34.39 | Improved |
| append the graph module to BIRNAT | BIRNAT · grayscale simulation | PSNR: 33.31 -> 33.83 | Improved |
| append the graph module to DDUN | DDUN · grayscale simulation | PSNR: 35.36 -> 36.28 | Improved |
| append the graph module to STFormer | STFormer · grayscale simulation | PSNR: 36.24 -> 37.28 | 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 2 of 2 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
- Memory-Efficient Network for Large-Scale Video Compressive Sensing (CVPR 2021 · similarity 0.91)
- Plug-and-Play Algorithms for Video Snapshot Compressive Imaging (TPAMI 2021 · similarity 0.88)
- EfficientSCI: Densely Connected Network With Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging (CVPR 2023 · similarity 0.88)
- MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing (CVPR 2021 · similarity 0.88)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.87)
- Reconstruction-free Cascaded Adaptive Compressive Sensing (CVPR 2024 · similarity 0.85)
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.
