# Event-to-Video Reconstruction using Spatio-Temporal and Frequency-Enhanced Deep Neural Networks

arXiv: https://arxiv.org/abs/2605.25804 · HTML: https://mlsanity.com/paper/2605.25804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 25 of 25)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [The Event-Camera Dataset and Simulator: Event-based Data for Pose Estimation, Visual Odometry, and SLAM](https://mlsanity.com/paper/1610.08336/) (2016)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning](https://mlsanity.com/paper/2207.04978/) (2022)
- [Wavelet Convolutions for Large Receptive Fields](https://mlsanity.com/paper/2407.05848/) (2024)
- [Recent Event Camera Innovations: A Survey](https://mlsanity.com/paper/2408.13627/) (2024)
- [CED: Color Event Camera Dataset](https://mlsanity.com/paper/1904.10772/) (2019)
- [HyperE2VID: Improving Event-Based Video Reconstruction via Hypernetworks](https://mlsanity.com/paper/2305.06382/) (2023)
- [Exploring Event Camera-based Odometry for Planetary Robots](https://mlsanity.com/paper/2204.05880/) (2022)
- [WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification](https://mlsanity.com/paper/2107.13335/) (2021)
- [EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction](https://mlsanity.com/paper/2305.00434/) (2023)
- [Motion Robust High-Speed Light-Weighted Object Detection With Event Camera](https://mlsanity.com/paper/2208.11602/) (2022)
- [Spiking Wavelet Transformer](https://mlsanity.com/paper/2403.11138/) (2024)
- [Temporal Residual Guided Diffusion Framework for Event-Driven Video Reconstruction](https://mlsanity.com/paper/2407.10636/) (2024)
- [Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation](https://mlsanity.com/paper/2407.10703/) (2024)
- [Event-Aided Time-to-Collision Estimation for Autonomous Driving](https://mlsanity.com/paper/2407.07324/) (2024)
- [Unlocking Fine-Grained Details with Wavelet-based High-Frequency Enhancement in Transformers](https://mlsanity.com/paper/2308.13442/) (2023)
- [Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT](https://mlsanity.com/paper/2501.06786/) (2025)

## Abstract (arXiv)

Event cameras offer significant advantages over conventional frame-based counterparts, including high temporal resolution, low latency, and energy efficiency. These characteristics make them suitable for high-speed and high-dynamic range scene acquisition scenarios; however, the lack of dense intensity frames limits the direct applicability of conventional computer vision methods for scene understanding. Event-to-video (E2V) reconstruction seeks to bridge this gap by converting asynchronous event streams into a sequence of synchronous video frames. Existing E2V reconstruction methods based on convolutional neural networks and transformers operate primarily in the spatial domain and often struggle to recover fine structural details while suppressing severe reconstruction artifacts. To address these issues, we propose MSFET-E2V, a novel multiscale frequency-enhanced transformer model. At its core lies a cross-domain attention module, which fuses spatio-temporal features with frequency-aware representations derived from the discrete wavelet transform. Unlike prior methods relying solely on spatial attention, our approach effectively captures both local and global structures by taking into account low- and high-frequency components, enhancing detail preservation and robustness across various motion scenarios. Furthermore, we propose a lightweight wavelet-enhanced skip block that serves as a skip connection, facilitating artifact suppression and structural detail refinement through joint spatial-frequency domain processing. Extensive experiments demonstrate that MSFET-E2V achieves superior performance over state-of-the-art methods on multiple real-world event datasets, offering significant gains in reconstruction quality. Moreover, compared to the existing transformer-based method, our proposed model significantly reduces the number of parameters, the GPU memory usage, and inference time.