Research map / Video / Video generation
SpikeDiff: Zero-shot High-Quality Video Reconstruction from Chromatic Spike Camera and Sub-millisecond Spike Streams
Siqi Yang, Jinxiu Liang, Zhaojun Huang, Yeliduosi Xiaokaiti, Yakun Chang, Zhaofei Yu, Boxin Shi
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 color casting operator C (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | FID: 12.064 -> 2.880 | Improved |
| add color casting operator C (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | PSNR: 16.752 -> 18.694 | Improved |
| add mosaicking operator M (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | PSNR: 17.481 -> 18.694 | Improved |
| add mosaicking operator M (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | FID: 4.392 -> 2.880 | Improved |
| add soft quantization operator Q (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | PSNR: 17.460 -> 18.694 | Improved |
| add soft quantization operator Q (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | IL-NIQE: 40.487 -> 38.535 | Improved |
| add color casting operator C (ablation) | SpikeDiff · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | IL-NIQE: 44.661 -> 38.535 | Improved |
| zero-shot diffusion posterior sampling instead of trained CSpkNet | SpikeDiff vs CSpkNet · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | PSNR: 13.364 -> 18.694 | Improved |
| zero-shot diffusion posterior sampling instead of trained CSpkNet | SpikeDiff vs CSpkNet · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | FID: 4.699 -> 2.880 | Improved |
| zero-shot diffusion instead of 3DRI | SpikeDiff vs 3DRI · Synthetic chromatic spikes (X4K1000FPS, 0.5ms) | SSIM: 0.390 -> 0.750 | Improved |
| SpikeDiff instead of SY24 on interpolation PSNR | SpikeDiff vs SY24 · Temporal consistency (synthetic, 0.5ms) | Interpolation PSNR: 28.65 -> 25.45 | Hurt |
| SpikeDiff instead of SY24 on interpolation error | SpikeDiff vs SY24 · Temporal consistency (synthetic, 0.5ms) | Interpolation error: 0.041 -> 0.057 | Hurt |
Closest papers by meaning
- Rethinking High-speed Image Reconstruction Framework with Spike Camera (AAAI 2025 · similarity 0.90)
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras (NeurIPS 2024 · similarity 0.88)
- Spk2SRImgNet: Super-Resolve Dynamic Scene from Spike Stream via Motion Aligned Collaborative Filtering (CVPR 2025 · similarity 0.87)
- USP-Gaussian: Unifying Spike-based Image Reconstruction, Pose Correction and Gaussian Splatting (CVPR 2025 · similarity 0.87)
- Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations (CVPR 2024 · similarity 0.87)
- SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams (NeurIPS 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.
