Shock Jiang
thank you for your feedback. I attached the DNG file together with three PNG files generated by SID, PS, and PS+blur. The exposure time of the DNG is 0.0333sec (1/30s)....
That's interesting. The sensor we used is Sony IMX 317, which is quite popular for cameras. As we can see, the output PNG brighten of whole photo at the cost...
@yueruchen The resolution of the photo is 3000x3000, which is not very low, compared to 4200x2800 photo provided by the author. This photo is noisy. @yueruchen @cchen156 Here I also...
which two files did you refer to? @yueruchen
what's more, acc-0.1d for nearly 100 percents. That is really amazing. Since diameter of those objects are around 10-20cm, that means almost all add are in 1-2cm. Really impressive.
@LeatherWang 请问这个mr merge之后，对于输入数据的坐标系是否有要求。例如： accel-0.csv: accel_x (m/s^2),accel_y (m/s^2),accel_z (m/s^2)， 是NED还是ENU？ gps-0.csv: gps_lat (deg),gps_lon (deg),gps_alt (m),gps_vN (m/s),gps_vE (m/s),gps_vD (m/s)，是否依然可以？注意，此处速度为NED gyro-0.csv：gyro_x (deg/s),gyro_y (deg/s),gyro_z (deg/s)：相对于IMU body frame的坐标系，or ENU?
@ideafold 请问关于坐标系的问题梳理清楚了吗？我遇到了类似的困惑。
not really. finally, I implement it myself, but in the method proposed in the paper. On Wed, Jun 27, 2018 at 3:39 PM Stupid Fish wrote: > @shockjiang hi, am...
it's not bad. the loss decreased from 0.64 to 0.62 while the flop reduce to 78%. On Wed, Jun 27, 2018 at 9:59 PM Stupid Fish wrote: > @shockjiang GREAT!Does...