Chenyang Shi

Gaussian Splatting SLAM (GS-SLAM) offers a notable improvement over traditional SLAM methods, in enabling photorealistic 3D reconstruction that conventional approaches often struggle to achieve. However, existing GS-SLAM systems perform poorly under persistent and severe motion blur commonly encountered in real-world scenarios, leading to significantly degraded tracking accuracy and compromised 3D reconstruction quality. To address this limitation, we propose EGS-SLAM, a novel GS-SLAM framework that fuses event data with RGB-D inputs to simultaneously reduce motion blur in images and compensate for the sparse, discrete nature of event streams, enabling robust tracking and high-fidelity 3DGS reconstruction. Specifically, our system explicitly models the camera's continuous trajectory during exposure, supporting event and blur-aware tracking and mapping on a unified 3DGS scene. Furthermore, we introduce a learnable camera response function to align the dynamic ranges of events and images, along with a no-event loss to suppress ringing artifacts during reconstruction. We validate our approach on a new dataset comprising synthetic and real-world sequences with significant motion blur. Extensive experimental results demonstrate that EGS-SLAM consistently outperforms existing GS-SLAM systems in both trajectory accuracy and photorealistic 3DGS reconstruction.

Event cameras are renowned for their high efficiency due to outputting a sparse, asynchronous stream of events. However, they are plagued by noisy events, especially in low light conditions. Denoising is an essential task for event cameras, but evaluating denoising performance is challenging. Label-dependent denoising metrics involve artificially adding noise to clean sequences, complicating evaluations. Moreover, the majority of these metrics are monotonic, which can inflate scores by removing substantial noise and valid events. To overcome these limitations, we propose the first label-free and non-monotonic evaluation metric, the area of the continuous contrast curve (AOCC), which utilizes the area enclosed by event frame contrast curves across different time intervals. This metric is inspired by how events capture the edge contours of scenes or objects with high temporal resolution. An effective denoising method removes noise without eliminating these edge-contour events, thus preserving the contrast of event frames. Consequently, contrast across various time ranges serves as a metric to assess denoising effectiveness. As the time interval lengthens, the curve will initially rise and then fall. The proposed metric is validated through both theoretical and experimental evidence. The codes are available at https://github.com/shicy17/AOCC.

Neuromorphic Vision Sensors (NVS) have raised increasing attention due to their sparsity, low latency, and high dynamic range. However, they suffer from the background activity noise which causes unnecessary computational waste. Existing learning-based denoising methods usually achieve better performance than rule-based methods but require larger computational and storage resources. To make rule-based filters as competitive as learning-based filters, this paper proposes a novel filter, namely the Event-based Bilateral Filter (EBF) that utilizes both spatiotemporal and polarity information. EBF first assigns two types of weights to each nearest neighborhood pixel based on the temporal and polarity information of the event to be classified. Next, EBF multiplies and accumulates the weights to get a correlation score, which is then compared with a threshold to predict the label of the event. We evaluate the proposed methods on three neuromorphic datasets, including both simulated data and real-world data. EBF significantly improves the denoising accuracy compared with rule-based filters and can exceed or compete with learning-based methods across different noise levels. The corresponding codes, datasets, and results are available at https://github.com/shicy17/EBF.

Event cameras, which are highly sensitive to light intensity changes, often generate substantial noise during imaging. Existing denoising methods either lack the speed for real-time processing or struggle with dynamic scenes, mistakenly discarding valid events. To address these issues, we propose a novel dual-stage polarity-focused denoising (PFD) method that leverages the consistency of polarity and its changes within local pixel areas. Whether due to camera motion or dynamic scene changes, the polarity and its changes in triggered events are highly correlated with these movements, allowing for effective noise handling. We introduce two versions: PFD-A, which excels at reducing background activity (BA) noise, and PFD-B, which is designed to address both BA and flicker noise. Both versions are lightweight and computationally efficient. The experimental results show that PFD outperforms benchmark methods in terms of the SNR and ESR metrics, achieving state-of-the-art performance across various datasets. Additionally, we propose an FPGA implementation of PFD processes that handles each event in just 7 clock cycles, ensuring real-time performance. The codes are available at https://github.com/shicy17/PFD.

Light interference negatively impacts on frame-based visual tasks. Phenomena such as overexposure cause the loss of valuable information and reduce task execution efficiency. Event cameras are neuromorphic vision sensors that output sparse, asynchronous streams of events rather than frames. These cameras feature high temporal resolution, high dynamic range, and low power consumption. As a result, they are not susceptible to overexposure and motion blur, and they are able to recognize light interference such as strobe lights, stray lights, and reflections. However, event cameras are highly sensitive to light intensity changes, so light interference still affects event cameras as noise which easily alias with events triggered by environmental objects. Therefore, to reduce or eliminate the negative impact of light interference on event cameras, we systematically analyze the optical properties and event-triggering principles of these forms of light interference, and then propose ELIR (Event-based Light Interference Removal) method for removing light interference signals in event streams under static and dynamic scenes. The proposed method is validated in object detection tasks. Additionally, we launch the LIED datasets to evaluate the effect of light interference removal in event streams to assist with other studies in this field. Experimental results on the LIED datasets show that our proposed method can remove, on average, over 97% of light interference in static scenes, over 86% in dynamic scenes. Finally, the proposed method is verified on the object detection task, achieving an average PRE over 92%. The dataset is available at https://github.com/shicy17/LIED.

Vibration measurement is an important part of monitoring the movement of objects and the working state of equipment. Non-contact vibration measurement can be achieved without installing a measuring device on the object to be measured, thus it has stronger applicability. However, traditional non-contact measurement methods, such as frame-based visual measurement, are prone to motion blur and difficult data processing. Event cameras encode the relative change of light intensity rather than the absolute value of the intensity recorded by conventional cameras, and this unique imaging mechanism makes them stand out with no motion blur, high temporal resolution and low power consumption. The displacement produced by the vibration of the object causes changes in light intensity, which are naturally captured by the event camera. Therefore, the use of event camera for vibration frequency measurement has inherent advantages. However, existing event-based methods cannot work under unstable lighting conditions, because changes in ambient light trigger events and interfere with the generation of events triggered by changes in light intensity produced by vibrations. Moreover, existing event-based computational methods do not model the mapping relationship between events and vibrations, the results of which are thus inaccurate. This article presents a method that utilizes laser-assisted illumination to help measure vibration frequencies. At the same time, a mixture Gaussian distribution is proposed to fit the frequency distribution. The experimental results show that the proposed method achieves accurate non-contact vibration frequency measurement of the object fixed on a vibrating table in the measurement range from 20 Hz to 300 Hz, with a relative error of 6.23 ‰, 4.03 ‰ and 5.45 ‰ under the ambient lighting of 0.01 lux, 55 lux and 3800 lux respectively. Furthermore, the measurement results of the vibration frequency of the loudspeaker show that the proposed method can measure the vibration in multiple directions.