Research map / Architectures and efficiency / RNNs and normalization
Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera
Lujie Xia, Ziluo Ding, Rui Zhao, Jiyuan Zhang, Lei Ma, Zhaofei Yu, Tiejun Huang, Ruiqin Xiong
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 dynamic timing representation (dilated conv) to PWC-Net(variant), supervised | PWC-Net(variant) · PHM dt=10 | mean AEE: 1.326 -> 0.854 | Improved |
| add dynamic timing representation to RAFT, supervised | RAFT · PHM dt=20 | mean AEE: 1.904 -> 1.649 | Improved |
| replace dilated convolution with normal convolution of same size (ablation) | RAFT · PHM dt=10 | mean AEE: 0.965 -> 1.220 | Hurt |
| replace dilated convolution with normal convolution | PWC-Net(variant) · PHM dt=10 | mean AEE: 1.326 -> 0.932 | Improved |
| use dilated convolutions instead of normal convolutions (ablation) | PWC-Net(variant) · PHM dt=10 | mean AEE: 0.932 -> 0.854 | Improved |
| add layer attention on top of TMR (ablation) | USFlow(pwc) · PHM dt=10 supervised | mean AEE: 0.888 -> 0.854 | Improved |
| add layer attention on top of TMR (ablation) | USFlow(pwc) · PHM dt=20 supervised | mean AEE: 1.699 -> 1.723 | Hurt |
| add layer attention on top of TMR (ablation) | USFlow(pwc) · PHM dt=10 unsupervised | mean AEE: 1.355 -> 1.307 | Improved |
| add timing representation (TMR) to USFlow(pwc) (ablation) | USFlow(pwc) · PHM dt=10 unsupervised | mean AEE: 1.783 -> 1.355 | Improved |
| proposed unsupervised loss instead of SSIM | USFlow(pwc) · PHM dt=20 unsupervised | mean AEE: 3.446 -> 2.413 | Improved |
| proposed unsupervised loss instead of Census | USFlow(pwc) · PHM dt=10 unsupervised | mean AEE: 1.759 -> 1.307 | Improved |
| remove I_T term from unsupervised loss (ablation) | USFlow(pwc) · PHM dt=10 unsupervised | mean AEE: 1.307 -> 2.071 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- RAFT — RAFT: Recurrent All-Pairs Field Transforms for Optical Flow (ECCV 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Spike Camera Optical Flow Estimation Based on Continuous Spike Streams (TPAMI 2025 · similarity 0.92)
- Learning Optical Flow from Continuous Spike Streams (NeurIPS 2022 · similarity 0.92)
- Optical Flow for Spike Camera with Hierarchical Spatial-Temporal Spike Fusion (AAAI 2024 · similarity 0.88)
- Recognizing Ultra-High-Speed Moving Objects with Bio-Inspired Spike Camera (AAAI 2024 · similarity 0.88)
- SpikeNeRF: Learning Neural Radiance Fields from Continuous Spike Stream (CVPR 2024 · similarity 0.87)
- Rethinking High-speed Image Reconstruction Framework with Spike Camera (AAAI 2025 · similarity 0.87)
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.
