# See Silhouettes in Motion with Neuromorphic Vision

arXiv: https://arxiv.org/abs/2605.17984 · HTML: https://mlsanity.com/paper/2605.17984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 55 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 26 of 26)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Event-based Vision: A Survey](https://mlsanity.com/paper/1904.08405/) (2019)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [High Speed and High Dynamic Range Video with an Event Camera](https://mlsanity.com/paper/1906.07165/) (2019)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation](https://mlsanity.com/paper/1804.01306/) (2018)
- [Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera](https://mlsanity.com/paper/1811.10180/) (2018)
- [Event-Based Fusion for Motion Deblurring with Cross-modal Attention](https://mlsanity.com/paper/2112.00167/) (2021)
- [Continuous-time Intensity Estimation Using Event Cameras](https://mlsanity.com/paper/1811.00386/) (2018)
- [Graph-Based Blind Image Deblurring From a Single Photograph](https://mlsanity.com/paper/1802.07929/) (2018)
- [Event Camera Calibration of Per-pixel Biased Contrast Threshold](https://mlsanity.com/paper/2012.09378/) (2020)
- [A selectional auto-encoder approach for document image binarization](https://mlsanity.com/paper/1706.10241/) (2017)
- [EventAid: Benchmarking Event-aided Image/Video Enhancement Algorithms with Real-captured Hybrid Dataset](https://mlsanity.com/paper/2312.08220/) (2023)
- [Event-based Stereo Depth Estimation: A Survey](https://mlsanity.com/paper/2409.17680/) (2024)
- [Deblurring Neural Radiance Fields with Event-driven Bundle Adjustment](https://mlsanity.com/paper/2406.14360/) (2024)
- [EventLFM: Event Camera integrated Fourier Light Field Microscopy for Ultrafast 3D imaging](https://mlsanity.com/paper/2310.00730/) (2023)
- [Neuromorphic Imaging with Joint Image Deblurring and Event Denoising](https://mlsanity.com/paper/2309.16106/) (2023)
- [Drone Detection with Event Cameras](https://mlsanity.com/paper/2508.04564/) (2025)
- [DeepTag: A General Framework for Fiducial Marker Design and Detection](https://mlsanity.com/paper/2105.13731/) (2021)
- [Event Encryption: Rethinking Privacy Exposure for Neuromorphic Imaging](https://mlsanity.com/paper/2306.03369/) (2023)
- [Event Camera Meets Mobile Embodied Perception: Abstraction, Algorithm, Acceleration, Application](https://mlsanity.com/paper/2503.22943/) (2025)
- [Dark-EvGS: Event Camera as an Eye for Radiance Field in the Dark](https://mlsanity.com/paper/2507.11931/) (2025)
- [CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective Invariants](https://mlsanity.com/paper/2310.13320/) (2023)
- [Neuromorphic Synergy for Video Binarization](https://mlsanity.com/paper/2402.12644/) (2024)
- [Neuromorphic Imaging with Super-Resolution](https://mlsanity.com/paper/2407.05764/) (2024)
- [Reading in the Dark with Foveated Event Vision](https://mlsanity.com/paper/2506.06918/) (2025)

## Abstract (arXiv)

Quasi-bimodal objects, such as text, road signs, and barcodes, play a basic yet vital role in daily visual communication. By boiling these down to clear silhouettes, binarization uses a minimal language to convey essential vision cues for maximum downstream efficiency, especially for tasks that require simple geometric, topological reasoning rather than heavy appearance modeling. The catch is that frame-based imaging often struggles on mobile platforms like drones, self-driving cars, and underwater vehicles, in which rapid motion causes severe motion blur and harsh lighting washes out scene details. To overcome these physical limits, neuromorphic vision via event cameras, featuring microsecond time resolution and high dynamic range, steps in as a natural solution. Building upon this event-driven paradigm, we propose a simple yet effective dual-modal approach that harnesses the synergy between frames and events for training-free, real-time, high-frame-rate binarization on CPU-only devices. Extensive evaluations show that it earns competitive performance against leading techniques in reducing blur artifacts and delivers impressive improvements under challenging illumination at a lower computational cost. Besides, its asynchronous nature bypasses long-standing event-scarcity issues that break traditional time-binning reconstruction at fixed time slots, maintaining clear target shapes even at extreme kilohertz frame rates. Its binary results further serve as reliable representations to facilitate a range of downstream tasks. This work paves the way towards lightweight perception and interaction in embodied intelligence on resource-constrained edge platforms.