Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Neuromorphic Imaging with Joint Image Deblurring and Event Denoising

About

Neuromorphic imaging reacts to per-pixel brightness changes of a dynamic scene with high temporal precision and responds with asynchronous streaming events as a result. It also often supports a simultaneous output of an intensity image. Nevertheless, the raw events typically involve a large amount of noise due to the high sensitivity of the sensor, while capturing fast-moving objects at low frame rates results in blurry images. These deficiencies significantly degrade human observation and machine processing. Fortunately, the two information sources are inherently complementary -- events with microsecond-level temporal resolution, which are triggered by the edges of objects recorded in a latent sharp image, can supply rich motion details missing from the blurry one. In this work, we bring the two types of data together and introduce a simple yet effective unifying algorithm to jointly reconstruct blur-free images and noise-robust events in an iterative coarse-to-fine fashion. Specifically, an event-regularized prior offers precise high-frequency structures and dynamic features for blind deblurring, while image gradients serve as a kind of faithful supervision in regulating neuromorphic noise removal. Comprehensively evaluated on real and synthetic samples, such a synergy delivers superior reconstruction quality for both images with severe motion blur and raw event streams with a storm of noise, and also exhibits greater robustness to challenging realistic scenarios such as varying levels of illumination, contrast and motion magnitude. Meanwhile, it can be driven by much fewer events and holds a competitive edge at computational time overhead, rendering itself preferable as available computing resources are limited. Our solution gives impetus to the improvement of both sensing data and paves the way for highly accurate neuromorphic reasoning and analysis.

Pei Zhang, Haosen Liu, Zhou Ge, Chutian Wang, Edmund Y. Lam• 2023

Related benchmarks

TaskDatasetResultRank
BinarizationHQF Gentle Light
MCC0.52
11
BinarizationHQF Bright Glare
MCC0.35
11
BinarizationREBlur Gentle Light
MCC0.71
11
BinarizationEBT Gentle Light
MCC0.65
11
BinarizationEBT Low Light
MCC0.32
11
BinarizationEBT Bright Glare
MCC41
11
BinarizationHQF Low Light
MCC23
11
BinarizationREBlur Low Light
MCC0.3
11
BinarizationREBlur Bright Glare
MCC39
11
Fiducial Marker TrackingHQF & EBT Gentle Light 1.0 (test)
RMSE1.72
5
Showing 10 of 18 rows

Other info

Follow for update