Efficient Event Stream Super-Resolution with Recursive Multi-Branch Fusion

Authors: Quanmin Liang, Zhilin Huang, Xiawu Zheng, Feidiao Yang, Jun Peng, Kai Huang, Yonghong Tian

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate that our approach achieves over 17% and 31% improvement on synthetic and real datasets, accompanied by a 2.3 acceleration. Furthermore, we evaluate our method on two downstream event-driven applications, i.e., object recognition and video reconstruction, achieving remarkable results that outperform existing methods.
Researcher Affiliation Academia 1School of Computer Science and Engineering, Sun Yat-Sen University 2Peng Cheng Laboratory 3Shenzhen International Graduate School, Tsinghua University 4Peking University
Pseudocode No No clearly labeled 'Pseudocode' or 'Algorithm' block or figure was found in the paper.
Open Source Code Yes Our code and Supplementary Material are available at https://github.com/Lqm26/RMFNet.
Open Datasets Yes Event NFS [Duan et al., 2021] is the first dataset to include LR-HR pairs captured through a designed display-camera system... we utilized an event simulator [Lin et al., 2022] to transform the NFS dataset [Kiani Galoogahi et al., 2017] and RGB-DAVIS dataset [Wang et al., 2020b] into event data, resulting in NFS-syn and RGB-syn datasets.
Dataset Splits Yes To evaluate the model s generalization, we select a subset of NFS-syn data for 2(4, 8) SR training and then validate on both the NFS-syn and RGB-syn datasets.
Hardware Specification Yes All experiments were conducted on a Tesla V100 GPU.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x) were explicitly stated in the paper.
Experiment Setup Yes We set T = 9 and use Mean Squared Error (MSE) to calculate the loss: ... For a fair comparison, we maintained training settings consistent with [Weng et al., 2022].