祝贺实验室 3 项科研成果发表在 AAAI 2025!


Date
Apr 11, 2025 12:00 AM

热烈祝贺开大纯同学、李和倍同学、吴沛熹同学!近期,实验室共有 3 项科研成果正式发表。

Event-enhanced blurry video super-resolution

祝贺开大纯同学!该论文已发表在 Proceedings of the AAAI Conference on Artificial Intelligence 39 (4), 4175-4183。

  • 作者: Dachun Kai、Yueyi Zhang、Jin Wang、Zeyu Xiao、Zhiwei Xiong、Xiaoyan Sun
  • 发表载体: Proceedings of the AAAI Conference on Artificial Intelligence 39 (4), 4175-4183
  • 发表时间: 2025年4月11日
  • 相关链接: 论文链接 · PDF · 代码

论文介绍

In this paper, we tackle the task of blurry video super-resolution (BVSR), aiming to generate high-resolution (HR) videos from low-resolution (LR) and blurry inputs. Current BVSR methods often fail to restore sharp details at high resolutions, resulting in noticeable artifacts and jitter due to insufficient motion information for deconvolution and the lack of high-frequency details in LR frames. To address these challenges, we introduce event signals into BVSR and propose a novel event-enhanced network, Ev-DeblurVSR. To effectively fuse information from frames and events for feature deblurring, we introduce a reciprocal feature deblurring module that leverages motion information from intra-frame events to deblur frame features while reciprocally using global scene context from the frames to enhance event features. Furthermore, to enhance temporal consistency, we propose a hybrid deformable alignment module that fully exploits the complementary motion information from inter-frame events and optical flow to improve motion estimation in the deformable alignment process. Extensive evaluations demonstrate that Ev-DeblurVSR establishes a new state-of-the-art performance on both synthetic and real-world datasets. Notably, on real data, our method is 2.59 dB more accurate and 7.28× faster than the recent best BVSR baseline FMA-Net.


Efficient event-based semantic segmentation via exploiting frame-event fusion: A hybrid neural network approach

祝贺李和倍同学!该论文已发表在 AAAI 39(17)。

Efficient event-based semantic segmentation via exploiting frame-event fusion: A hybrid neural network approach

  • 作者: Hebei Li、Yansong Peng、Jiahui Yuan、Peixi Wu、Jin Wang、Yueyi Zhang、Xiaoyan Sun
  • 发表载体: AAAI 39(17)
  • 发表时间: 2025年4月11日
  • 相关链接: 论文链接 · PDF

论文介绍

本文提出一种高效的混合神经网络框架,用于事件相机语义分割。该框架包含处理事件流的脉冲神经网络(SNN)分支和处理帧图像的人工神经网络(ANN)分支,并设计了自适应时间加权(ATW)注入器、事件驱动稀疏(EDS)注入器和通道选择融合(CSF)模块,以充分融合帧与事件的互补时空信息。在DDD17-Seg、DSEC-Semantic和M3ED-Semantic数据集上取得了最先进精度,并在DSEC-Semantic上降低63%能耗。


Spiking point transformer for point cloud classification

祝贺吴沛熹同学!该论文已发表在 AAAI 39(20)。

Spiking point transformer for point cloud classification

  • 作者: Peixi Wu、Bosong Chai、Hebei Li、Menghua Zheng、Yansong Peng、Zeyu Wang、Xuan Nie、Yueyi Zhang、Xiaoyan Sun
  • 发表载体: AAAI 39(20)
  • 发表时间: 2025年4月11日
  • 相关链接: 论文链接 · PDF · 代码

论文介绍

本文提出Spiking Point Transformer(SPT),首个基于Transformer的脉冲神经网络框架,用于三维点云分类。SPT设计队列驱动采样直接编码,在降低计算成本的同时保留关键支撑点;并引入混合动力学积分发放神经元(HD-IF),模拟选择性神经元激活,减少对特定人工神经元的过度依赖。在多个真实与合成点云基准上取得领先结果,理论能耗较ANN对应模型降低至少6.4倍。

开大纯
开大纯
毕业生
李和倍
李和倍
博士生
吴沛熹
吴沛熹
博士生