paper-with-me

홈 › Papers

CompEvent: Complex-valued Event-RGB Fusion for Low-light Video Enhancement and Deblurring

2025-11-18 · Mingchen Zhong, Xin Lu, Dong Li, Senyan Xu, Ruixuan Jiang, Xueyang Fu, Baocai Yin arxiv

Low-light video deblurring poses significant challenges in applications like nighttime surveillance and autonomous driving due to dim lighting and long exposures. While event cameras offer potential solutions with superior low-light sensitivity and high temporal resolution, existing fusion methods typically employ staged strategies, limiting their effectiveness against combined low-light and motion blur degradations. To overcome this, we propose CompEvent, a complex neural network framework enabling holistic full-process fusion of event data and RGB frames for enhanced joint restoration. CompEvent features two core components: 1) Complex Temporal Alignment GRU, which utilizes complex-valued convolutions and processes video and event streams iteratively via GRU to achieve temporal alignment and continuous fusion; and 2) Complex Space-Frequency Learning module, which performs unified complex-valued signal processing in both spatial and frequency domains, facilitating deep fusion through spatial structures and system-level characteristics. By leveraging the holistic representation capability of complex-valued neural networks, CompEvent achieves full-process spatiotemporal fusion, maximizes complementary learning between modalities, and significantly strengthens low-light video deblurring capability. Extensive experiments demonstrate that CompEvent outperforms SOTA methods in addressing this challenging task.

📄 PDF Abstract BibTeX arXiv:2511.14469

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingVideo Enhancement

Similar Papers 제목 키워드 기반

Complex Diffusion Maps with $ω$-Parameterized Kernels Revealing Inherent Harmonic Representations

2026-05-03 · Tongzhen Dang, Weiyang Ding, Michael K. Ng arxiv

In this paper, we propose Complex Diffusion Maps (CDM), a novel diffusion mapping framework that aims to reveal the dominant complex harmonics of high-dimensional data. Inspired by the local Gaussian kernel relevant to t…

Computational Efficiency

Fully Complex-valued Fully Convolutional Multi-feature Fusion Network (FC2MFN) for Building Segmentation of InSAR images

2022-12-14 · Aniruddh Sikdar, Sumanth Udupa, Suresh Sundaram, Narasimhan Sundararajan

Building segmentation in high-resolution InSAR images is a challenging task that can be useful for large-scale surveillance. Although complex-valued deep learning networks perform better than their real-valued counterpar…

SegmentationSemantic Segmentation

Adversarial Audio Synthesis with Complex-valued Polynomial Networks

2022-06-14 · Yongtao Wu, Grigorios G Chrysos, Volkan Cevher

Time-frequency (TF) representations in audio synthesis have been increasingly modeled with real-valued networks. However, overlooking the complex-valued nature of TF representations can result in suboptimal performance a…

Audio GenerationAudio Synthesis

Unified Complex-valued Neural Network: A Magnitude-Phase Computational Model for Event-Driven Neuromorphic Learning

2026-06-27 · Reza Ahmadvand, Sarah Safura Sharif, Yaser Mike Banad arxiv

Artificial neural networks (ANN) provide accurate continuous-valued representation, whereas spiking neural networks (SNN) offer event-driven temporal processing, yet both paradigms face limitations when value encoding an…

Object Tracking

HyperReal: Complex-Valued Layer Functions For Complex-Valued Scaling Invariance

2021-01-01 · Utkarsh Singhal, Yifei Xing, Stella Yu

Complex-valued measurements in MRI and SAR imaging often have complex-valued scaling ambiguity, calling for models that are invariant to complex-valued scaling of pixels. Deep Complex Networks (DCN) extends real-valued a…