Xuran Pan (潘旭冉)

Results 6 comments of Xuran Pan (潘旭冉)

Hi! A possible solution might be setting a lower **_chunk, netchunk_** or **_N_rand_** value. Also, if you happened to encounter this issue in the evaluation process, e.g., when generating videos,...

Yes. You can set args.i_testset or args.i_video with a proper value to enable visualization in the training process.

Hi! Thanks for your attention to our work. For the first concern, our example for lego or hotdog keeps 20 initial training samples while other 80 images are viewed as...

@YZsZY The data choice in our example is only a toy illustration. You can choose your own initial training set that most suitable for your method or task.

In our case, we see the uncertainty estimation as an attribute similar to volume density, thus we omit the influence of viewing direction. Also, this assumption helps us to meet...

Sorry for the inconvenience of the late reply, and we have now released the code. I will now close this issue and feel free to open another one if new...