This dataset is designed to evaluate event denoising algorithm performance against real sensor data. Data was collected using a DAVIS346 neuromorphic camera. Movement of the camera was restricted by a gimbal, and the IMU was calibrated before each collection. Only stationary scenes were selected, avoiding saturation and severe noise in the APS. We obtained 16 indoor and outdoor scenes of noisy, real-world data to form DVSNOISE20. Each scene was captured three times for ≈16 seconds, giving 48 total sequences with a wide range of motions. We provide the raw sensor data from each collect, processing and evaluation code, Event Probability Mask (EPM), features used for Event Denoising CNN (EDnCNN), and associated labels. For additional information please see the paper.

Please cite the CVPR 2020 paper... "Event Probability Mask (EPM) and Event Denoising Convolutional Neural Network (EDnCNN) for Neuromorphic Cameras"

• Readme

• Code

  • Raw AEDAT data (Matlab Format)

  • Camera Distortion and Fixed Pattern Noise

• EPM

  • EDnCNN Features and Labels (Sample Video)

• Pretrained Network (Matlab Format)

This dataset is designed to enhance the progress event-based optical flow algorithms. The data was collected using using IniVation DAViS346 camera, which has a 346 x 260 spatial resolution. The dataset is classified into camera motion data (stationary scene and moving camera) and object motion data (stationary camera and moving objects). The camera motion data contains four real indoor sequences (namely, checkerboard, classroom, conference room, and conference room translation) with ground truth motion inferred from IMU. The movement of the camera in this category was restricted by a gimbal, and the IMU was calibrated before each collection. The object motion data includes two real sequences (called hands and cars) containing multiple object motions. This category does not have ground truth motion since the object motion cannot be inferred from IMU. For additional information please see the paper.

Please cite the ICCP 2020 paper ... "Distance Surface for Event-Based Optical Flow" .

• Readme

  • Code

• Original Raw AEDAT4 file

• Camera Motion Data (mat files)

• Object Motion Data (mat files)

• Camera Distortion