How to run ENeRF on my own data?

[whuzjw]

Hi, the real-time dynamic rendering demo on your project page is so cool! And I want to make the same thing on my own data (sequence of images). What should I do?

[whuzjw]

I found a script named colmap2mvsnet.py in MVSNet, which may solve the problem. I wonder if you also use this script and whether there is a better way to do so. If you could provide a script and a guide on README, that's better😁.

[whuzjw]

I also want to confirm that ENeRF can generate a frame at any time, right? For example, synthesize a frame at a novel time t1.5 that is not in the discrete time {t0, t1, t2...} of the training frames.

[haotongl]

Thank you for your attention! We will release the interactive rendering, other scripts and a guide on how to run enerf on custom data soon. (Expected in the weekend.)

[haotongl]

I also want to confirm that ENeRF can generate a frame at any time, right? For example, synthesize a frame at a novel time t1.5 that is not in the discrete time {t0, t1, t2...} of the training frames.

ENeRF only generates a frame in the discrete time. A 60FPS video provides very high continuity, and usually does not require us to perform interpolation to obtain continuity.

[JokerYan]

Thank you very much for the plan of releasing such a guide. May I ask whether you can include the instructions to run the "compositional ENeRF" in the guide as well. I guess it is crucial to render a high quality video as shown in your project page, but is unfortunately only briefly mentioned in the paper supplementary.

[haotongl]

Thank you very much for the plan of releasing such a guide. May I ask whether you can include the instructions to run the "compositional ENeRF" in the guide as well. I guess it is crucial to render a high quality video as shown in your project page, but is unfortunately only briefly mentioned in the paper supplementary.

Yeah, we will release the outdoor dataset we collected along with the corresponding code before this weekend.

[xiangdonglai]

Would you release the dataloader for ZJU-MoCap/DynamicCap, too? Thanks in advance.

[haotongl]

We have released the dataloader for ZJU-MoCap. Thanks for your attention!

[kjzju]

Thank you for your great work. I wonder when you will release the outdoor dataset you collected along with the corresponding code.

[junsukha]

Thank you for your attention! We will release the interactive rendering, other scripts and a guide on how to run enerf on custom data soon. (Expected in the weekend.)

Hi! Thanks for sharing the work!
Has the guide on how to run enerf on custom data been released? I can't fine one.