Research map / Probabilistic and scientific modeling / Dynamical systems
SpikeGen: Decoupled “Rods and Cones” Visual Representation Processing with Latent Generative Framework
Gaole Dai, Menghang Dong, Rongyu Zhang, Ruichuan An, Tiejun Huang, Shanghang Zhang
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 TFP pseudo-dense frame to spike input (ablation) | SpikeGen · SREDS | PSNR: 33.62 -> 39.25 | Improved |
| use TFP instead of TFI as pseudo-dense frame (ablation) | SpikeGen · SREDS | PSNR: 37.19 -> 39.25 | Improved |
| add spike modality to RGB deblurring (SpikeGen vs strongest baseline) as spikes get sparser | SpikeGen · GOPRO deblurring Vth=4 | PSNR: 25.43 -> 28.07 | Improved |
| pre-train latent generative model on ImageNet with random modality dropout | SpikeGen · GOPRO deblurring with sparse spikes | PSNR | Improved |
| use SpikeGen instead of SpikeGS on novel-view synthesis | 3DGS pipeline · Blender (average) | PSNR: 29.12 -> 30.04 | Improved |
| use SpikeGen instead of DeblurNeRF on outdoor scenes | Novel-view synthesis · Blender Out-Door | PSNR: 28.77 -> 28.26 | Hurt |
| simplify auto-regressive MAR generation to generating all tokens at once (ablation) | SpikeGen · general | overall performance | No clear effect |
| use fewer spike frames (16 vs 64) with TFP prior | SpikeGen vs STIR · SREDS | PSNR: 38.79 -> 39.25 | Improved |
Closest papers by meaning
- Finding Visual Saliency in Continuous Spike Stream (AAAI 2024 · similarity 0.87)
- SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream (CVPR 2024 · similarity 0.86)
- Rethinking High-speed Image Reconstruction Framework with Spike Camera (AAAI 2025 · similarity 0.86)
- Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli (NeurIPS 2024 · similarity 0.86)
- Latent Space Imaging (CVPR 2025 · similarity 0.85)
- Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity (NeurIPS 2025 · 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.
