Research map / Video / Video segmentation and tracking
Event-Based Video Reconstruction Using Transformer
Wenming Weng, Yueyi Zhang, Zhiwei Xiong
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 Token Pyramid Aggregation (vs E2VID-res12 with similar parameters) (ablation) | ET-Net-4-s4 · MVSEC | MSE: 0.169 -> 0.118 | Improved |
| add Token Pyramid Aggregation (vs E2VID-res12 with similar parameters) (ablation) | ET-Net-4-s4 · MVSEC | SSIM: 0.309 -> 0.355 | Improved |
| add Token Pyramid Aggregation (vs E2VID-res6 with similar parameters) (ablation) | ET-Net-2-s4 · MVSEC | MSE: 0.165 -> 0.113 | Improved |
| use 4 aggregation scales instead of a single scale in TPA (ablation) | ET-Net · IJRR | MSE: 0.0991 -> 0.0552 | Improved |
| use 4 aggregation scales instead of 3 in TPA (ablation) | ET-Net · IJRR | MSE: 0.0584 -> 0.0552 | Improved |
| use Transformer decoders instead of encoders for cross-scale dependency in TPA (ablation) | ET-Net-4-s4 · IJRR | MSE: 0.0563 -> 0.0522 | Improved |
| use Transformer decoders instead of encoders for cross-scale dependency in TPA (ablation) | ET-Net-4-s4 · MVSEC | MSE: 0.129 -> 0.118 | Improved |
| use Transformer decoders instead of encoders for cross-scale dependency in TPA (ablation) | ET-Net-4-s4 · HQF | MSE: 0.0399 -> 0.0403 | No clear effect |
| add skip connection between RCB and MLU (ablation) | ET-Net-4-s4 · MVSEC | LPIPS: 0.653 -> 0.491 | Improved |
| add skip connection between RCB and MLU (ablation) | E2VID-res12 · MVSEC | MSE: 0.179 -> 0.169 | Improved |
| use 4 Transformer encoders/decoders per scale rather than 2 (ablation) | ET-Net-s4 · HQF | MSE: 0.0413 -> 0.0403 | Improved |
| use 6 Transformer encoders/decoders per scale rather than 4 (ablation) | ET-Net-s4 · HQF | MSE: 0.0403 -> 0.0430 | Hurt |
Closest papers by meaning
- Events-To-Video: Bringing Modern Computer Vision to Event Cameras (CVPR 2019 · similarity 0.91)
- Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow (TPAMI 2022 · similarity 0.89)
- Reducing the Sim-to-Real Gap for Event Cameras (ECCV 2020 · similarity 0.89)
- Video to Events: Recycling Video Datasets for Event Cameras (CVPR 2020 · similarity 0.88)
- LaSe-E2V: Towards Language-guided Semantic-aware Event-to-Video Reconstruction (NeurIPS 2024 · similarity 0.87)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (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.
