Research map / Video / Video segmentation and tracking
Spike-Temporal Latent Representation for Energy-Efficient Event-to-Video Reconstruction
Jianxiong Tang, Jian-Huang Lai, Lingxiao Yang, Xiaohua Xie
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 |
|---|---|---|---|
| use STLR spiking latent coding instead of EVSNN | SNN-based E2V reconstruction · IJRR | MSE: 0.097 -> 0.075 | Improved |
| use STLR instead of EVSNN for energy cost | SNN-based E2V reconstruction · IJRR | energy (J): 2.28 × 10−2 -> 1.26 × 10−3 | Improved |
| STLR compared to ANN E2VID on IJRR MSE | STLR · IJRR | MSE: 0.064 -> 0.075 | Hurt |
| add fixed point approximation (FPA) loss (ablation) | STLR · Average over IJRR/HQF/MVSEC | MSE: 0.148 -> 0.104 | Improved |
| add FPA loss on HQF (ablation) | STLR · HQF | LPIPS: 0.400 -> 0.408 | Mixed |
| increase SVT unfolding steps from 5 to 10 (ablation) | STLR · Average over IJRR/HQF/MVSEC | MSE: 0.104 -> 0.089 | Improved |
| increase SVT unfolding steps from 5 to 8 (ablation) | STLR · Average over IJRR/HQF/MVSEC | MSE: 0.104 -> 0.117 | Hurt |
| choose decoder spiking neuron (LIF, PLIF, SPSN, SLTT) (ablation) | STLR decoder · Average over IJRR/HQF/MVSEC | MSE: 0.111 -> 0.104 | No clear effect |
| inject Poisson noise (lambda=0.1) into input events | STLR vs E2VID · IJRR | LPIPS: 0.566 -> 0.124 | Improved |
Closest papers by meaning
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.86)
- SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024 · similarity 0.86)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 2024 · similarity 0.86)
- Efficient 3D Recognition with Event-driven Spike Sparse Convolution (AAAI 2025 · similarity 0.85)
- Spiking Neural Network as Adaptive Event Stream Slicer (NeurIPS 2024 · similarity 0.85)
- Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras (NeurIPS 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.
