Question about event timestamps.

[shiba24]

Hi, thank you for the dataset.

When I load the event npz file, the timestamp looks strange (all integers). What's the actual unit of the timestamp?

import numpy as np
fname = '/home/ubuntu/slocal/ssd_data/EventNeRF/data/lego/test1_events/test/events/out.npz'

with np.load(fname) as data:
    ts = data['t']

ts[:10]     # returns array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
ts[-10:]    # returns array([999, 999, 999, 999, 999, 999, 999, 999, 999, 999])
len(np.unique(ts))  # returns 1000
ts.max()  # returns 999

I suspect that this integers [0-999] corresponds to the number of frames. If that is the case, this dataset does not contain accurate event timestamps, but rather has the ones quantized to the frame IDs?

[C19h]

I also found this problem in synthetic data sets. But it's normal in real data sets. It is hoped that the author can disclose the original event data of the synthetic dataset.

[r00tman]

Hi, sorry for the delay.

Yes, the timestamp is tied to the frame number. We render 1000 RGB frames at 1000 fps and then put them through the event camera simulator to get the event files.

We have original .blend files of the scenes on this page.

I could share the original rendered RGB frames too, then you would be able to directly use other event simulators, e.g., ones that do frame interpolation before simulation, resulting in less quantized timestamps.

[C19h]

Hi, sorry for the delay.

Yes, the timestamp is tied to the frame number. We render 1000 RGB frames at 1000 fps and then put them through the event camera simulator to get the event files.

We have original .blend files of the scenes on this page.

I could share the original rendered RGB frames too, then you would be able to directly use other event simulators, e.g., ones that do frame interpolation before simulation, resulting in less quantized timestamps.

Thank you very much for your dataset, I noticed that you provided the original file of the real sequence (.aedat4 file). The.aedat4 file for the synthetic dataset is not provided. I now really need the aedat4 file of the synthesized sequence to compare with your great work. Thank you! @r00tman