Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging

Wang, Zihao W.; Duan, Peiqi; Cossairt, Oliver; Katsaggelos, Aggelos K.; Huang, Tiejun; Shi, Boxin

doi:10.1109/cvpr42600.2020.00168

Cited by 75 publications

(23 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both cameras are hardware synchronized and share a similar field of view (FoV). We provide a detailed comparison of our setup against the commercially available DAVIS 346 [4] and the recently introduced setup [40] in the appendix.Compared to both [4] and [40] our setup is able to record events at much higher resolution (1280×720 vs. 240×180 or 346×260) and standard frames at much higher framerate (225 FPS vs. 40 FPS or 35 FPS) and with a higher dynamic range (71.45 dB vs. 55 dB or 60 dB). Moreover, standard frames have a higher resolution compared to the DAVIS sensor (1440×1080 vs. 240×180) and provide color.…”

Section: High Speed Events-rgb (Hs-ergb) Datasetmentioning

confidence: 99%

“…Those properties render it not ideal for many event based methods, which aim to outperform traditional frame based cameras in certain applications. The setup described in [40] shows improvements in the resolution of frames and dynamic range, but has a reduced event resolution instead. The lack of publicly available high resolution event and color frame datasets and of the shelf hardware motivated the development of our dual camera setup.…”

Section: High Speed Events and Rgb Datasetmentioning

confidence: 99%

“…It features high resolution, high frame rate, high dynamic range color frames combined with high resolution events. A comparison of our setup with the DAVIS346 [4] and the setup with beam splitter in [40] is shown in 7. With this new setup we collect new High Speed Events and RGB (HS-ERGB) Dataset that we summarize in Tab.…”

Section: High Speed Events and Rgb Datasetmentioning

confidence: 99%

“…Comparison of our HS-ERGB dataset against publicly available High Quality Frames (HQF) dataset, acquired by DAVIS 346[4] and Guided Event Filtering (GEF) dataset, acquired by setup with DAVIS240 and RGB camera mounted with beam splitter[40]. Note, that in contrast to the previous datasets, the proposed dataset has high resolution of event data, and high frame rate.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Time Lens: Event-based Video Frame Interpolation

Tulyakov

Gehrig

Georgoulis

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

138

View full text Add to dashboard Cite

indicates equal contribution Time Lens, a novel method that leverages the advantages of both. We extensively evaluate our method on three synthetic and two real benchmarks where we show an up to 5.21 dB improvement in terms of PSNR over state-of-the-art frame-based and event-based methods. Finally, we release a new large-scale dataset in highly dynamic scenarios, aimed at pushing the limits of existing methods.

show abstract

Section: High Speed Events-rgb (Hs-ergb) Datasetmentioning

confidence: 99%

Section: High Speed Events and Rgb Datasetmentioning

confidence: 99%

Section: High Speed Events and Rgb Datasetmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Time Lens: Event-based Video Frame Interpolation

Tulyakov

Gehrig

Georgoulis

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

138

View full text Add to dashboard Cite

show abstract

“…These benefits open up new paths in solving various vision problems. Event cameras have brought new solutions to many classical as well as novel problems in computer vision and robotics, including high frame-rate video reconstruction [1], [2], [3], with HDR [4], [5] and high resolution [6], [7], [8], and 3D reconstruction of human motion [9] and scenes [10], [11], as well as odometry [12], [13] and tracking [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Removing Blocking Artifacts in Video Streams Using Event Cameras

Chopp¹,

Banerjee²,

Cossairt³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we propose EveRestNet, a convolutional neural network designed to remove blocking artifacts in video streams using events from neuromorphic sensors. We first degrade the video frame using a quadtree structure to produce the blocking artifacts to simulate transmitting a video under a heavily constrained bandwidth. Events from the neuromorphic sensor are also simulated, but are transmitted in full. Using the distorted frames and the event stream, EveRestNet is able to improve the image quality.

show abstract

Multi‐Event‐Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Ghosh

Gallego

2022

Advanced Intelligent Systems

View full text Add to dashboard Cite

Event cameras are bio‐inspired sensors that offer advantages over traditional cameras. They operate asynchronously, sampling the scene at microsecond resolution and producing a stream of brightness changes. This unconventional output has sparked novel computer vision methods to unlock the camera's potential. Here, the problem of event‐based stereo 3D reconstruction for SLAM is considered. Most event‐based stereo methods attempt to exploit the high temporal resolution of the camera and the simultaneity of events across cameras to establish matches and estimate depth. By contrast, this work investigates how to estimate depth without explicit data association by fusing disparity space images (DSIs) originated in efficient monocular methods. Fusion theory is developed and applied to design multi‐camera 3D reconstruction algorithms that produce state‐of‐the‐art results, as confirmed by comparisons with four baseline methods and tests on a variety of available datasets.

show abstract

Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging

Cited by 75 publications

References 47 publications

Time Lens: Event-based Video Frame Interpolation

Time Lens: Event-based Video Frame Interpolation

Removing Blocking Artifacts in Video Streams Using Event Cameras

Multi‐Event‐Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion

Contact Info

Product

Resources

About