Research map / 3D vision / Depth and stereo
Spike Transformer: Monocular Depth Estimation for Spiking Camera
Jiyuan Zhang, Lulu Tang, Zhaofei Yu, Jiwen Lu, Tiejun Huang
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 |
|---|---|---|---|
| replace U-Net encoder with Spike-T transformer encoder | depth network · DENSE-spike test set | Abs Rel: 0.815 -> 0.606 | Improved |
| replace E2Depth ConvLSTM encoder with Spike-T transformer encoder | depth network · DENSE-spike test set | Abs Rel: 0.674 -> 0.606 | Improved |
| replace U-Net encoder with Spike-T transformer encoder | depth network · DENSE-spike val set | Abs Rel: 0.306 -> 0.262 | Improved |
| replace E2Depth encoder with Spike-T transformer encoder | depth network · DENSE-spike val set | Abs Rel: 0.291 -> 0.262 | Improved |
| replace E2Depth encoder with Spike-T | depth network · DENSE-spike test set | Sq Rel: 20.316 -> 18.388 | Improved |
| add local features to global-only temporal embedding (ablation) | Spike-T · DENSE-spike (temporal window ablation) | Abs Rel: 0.416 -> 0.376 | Improved |
| add global features to local-only temporal embedding (ablation) | Spike-T · DENSE-spike (temporal window ablation) | Abs Rel: 0.389 -> 0.376 | Improved |
| add global features to local-only temporal embedding (ablation) | Spike-T · DENSE-spike (temporal window ablation) | Sq Rel: 10.884 -> 9.265 | Improved |
| use local-only instead of global-only temporal features (ablation) | Spike-T · DENSE-spike (temporal window ablation) | RMS log: 0.478 -> 0.490 | Hurt |
| use local-only instead of global-only temporal features (ablation) | Spike-T · DENSE-spike (temporal window ablation) | Abs Rel: 0.416 -> 0.389 | Improved |
| replace Conv3D patch partition with S-T partition (ablation) | Spike-T · DENSE-spike test set | Abs Rel: 0.868 -> 0.606 | Improved |
| replace Conv3D patch partition with S-T partition (ablation) | Spike-T · DENSE-spike val set | Abs Rel: 0.310 -> 0.262 | Improved |
Closest papers by meaning
- Finding Visual Saliency in Continuous Spike Stream (AAAI 2024 · similarity 0.91)
- SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams (NeurIPS 2024 · similarity 0.89)
- SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream (CVPR 2024 · similarity 0.89)
- Rethinking High-speed Image Reconstruction Framework with Spike Camera (AAAI 2025 · similarity 0.89)
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras (NeurIPS 2024 · similarity 0.89)
- Boosting Spike Camera Image Reconstruction from a Perspective of Dealing with Spike Fluctuations (CVPR 2024 · similarity 0.88)
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.
