Research map / 3D vision / Depth and stereo
NeuSpike-Net: High Speed Video Reconstruction via Bio-Inspired Neuromorphic Cameras
Lin Zhu, Jianing Li, Xiao Wang, Tiejun Huang, Yonghong Tian
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 event data to spike data (ablation) | NeuSpike-Net · Simulated complex scenes | PSNR: 26.84 -> 27.40 | Improved |
| add spike data to event data (ablation) | NeuSpike-Net · Simulated complex scenes | PSNR: 12.85 -> 27.40 | Improved |
| add event data to spike-only reconstruction (ablation) | NeuSpike-Net · Real-world outdoor scenes | SSIM: 0.4682 -> 0.5046 | Improved |
| use integrate-and-fire event representation instead of event stacking (ablation) | NeuSpike-Net · Simulated data | PSNR: 29.35 -> 30.31 | Improved |
| use integrate-and-fire event representation instead of voxel grid (ablation) | NeuSpike-Net · Simulated data | PSNR: 29.44 -> 30.31 | Improved |
| add temporal ISI channel to spike representation (ablation) | NeuSpike-Net · Simulated data | PSNR: 27.65 -> 30.31 | Improved |
| use feature fusion module instead of element-wise sum (ablation) | NeuSpike-Net · Simulated data | PSNR: 29.74 -> 30.31 | Improved |
| use 3 encoders instead of 4 (ablation) | NeuSpike-Net · Simulated data | PSNR: 29.59 -> 30.31 | Improved |
| use 3 encoders instead of 2 (ablation) | NeuSpike-Net · Simulated data | PSNR: 30.26 -> 30.31 | No clear effect |
| use 2 residual blocks instead of 3 (ablation) | NeuSpike-Net · Simulated data | PSNR: 29.80 -> 30.31 | Improved |
| use L2 plus perceptual loss instead of L1 plus perceptual loss (ablation) | NeuSpike-Net · Simulated data | SSIM: 0.9297 -> 0.9234 | Mixed |
| add perceptual loss to L2 (ablation) | NeuSpike-Net · Simulated data | PSNR: 29.57 -> 30.31 | Improved |
Closest papers by meaning
- Ultra-High Temporal Resolution Visual Reconstruction From a Fovea-Like Spike Camera via Spiking Neuron Model (TPAMI 2022 · similarity 0.93)
- Rethinking High-speed Image Reconstruction Framework with Spike Camera (AAAI 2025 · similarity 0.88)
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras (NeurIPS 2024 · similarity 0.87)
- Spike-guided Motion Deblurring with Unknown Modal Spatiotemporal Alignment (CVPR 2024 · similarity 0.86)
- Optical Flow for Spike Camera with Hierarchical Spatial-Temporal Spike Fusion (AAAI 2024 · similarity 0.86)
- Recognizing Ultra-High-Speed Moving Objects with Bio-Inspired Spike Camera (AAAI 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.
