About the pipeline to video

[chikiuso]

Hi, I train and generate the result (.txt with lots of parameters), what's next to generate a video? How could I generate a video with the result? thanks.

[Ghostpepper123]

Hi, did you figure it out? I've been trying to figure this script out too. I'm currently trying to figure out what 'save_dir' is. Have you made any progress?

[0x10cxR1]

Hi @chikiuso, do you know how to deal with the txt results? Thanks!

[dvirsegal]

joining the question

[rragundez]

@supasorn I think this is an important issue. Could you comment on it?

[supasorn]

I'll try to get the pca basis (I just moved and don't have access now) which is used to produce the sparse shape. However, the pipeline is up to 10k lines of code and I might not have the bandwidth to publish them all in the near future.

[Mu7ammad]

@supasorn Yes please, having the PCA basis to be able to reconstruct the reference mouth landmarks will add great value to this repository, even without the rest of the mouth texture pipeline. Thanks for sharing these with us, and looking forward to this last piece.

[nikhitha-m]

@supasorn It would be a great help if you could share at least PCA basis for time being.

[chikiuso]

I got the data something like the following in the result folder, how could I turn it into a working video? thanks :

8941 21 0.012750 -14.305814 1.723046 -3.195284 0.839943 0.292246 0.310746 -0.673671 -0.035229 -0.497246 0.038055 -0.060966 -0.281909 0.200559 -0.007483 -0.090569 0.028182 -0.071471 -0.060519 -0.064697 0.053031 0.012750 -10.957369 0.370900 -4.028065 1.322961 -0.047874 -0.381775 -0.194586 -0.195218 -0.259842 -0.151549 0.010871 -0.246901 0.094218 -0.064462 -0.098995 -0.022320 -0.059445 -0.046436 -0.051390 0.033529 0.012750 -12.626245 0.770954 -3.939007 1.471983 0.298785 -0.459137 -0.174414 -0.107329 -0.370750 -0.217055 0.006996 -0.261211 0.154793 -0.053607 -0.107184 -0.020559 -0.124198 -0.060682 -0.090156 0.025293 0.012750 -11.888833 0.430780 -4.011168 1.658940 0.089108 -0.692530 -0.073704 -0.138650 -0.369726 -0.305787 0.005497 -0.214101 0.149432 -0.047078 -0.105292 -0.043473 -0.108837 -0.038625 -0.106557 0.012551 0.012750 -12.715007 0.538861 -3.877327 1.780462 0.109226 -0.668121 -0.107567 -0.095448 -0.421308 -0.334100 -0.005160 -0.202670 0.153702 -0.046681 -0.099228 -0.042577 -0.113163 -0.025554 -0.128626 0.001390 0.012750 -5.926603 1.824336 -4.906502 -0.294607 0.156135 -0.279463 0.000935 0.388505 -0.467345 0.117154 0.056054 -0.067724 -0.023136 -0.003218 -0.000294 -0.082321 -0.062127 -0.175327 -0.092154 0.078000

[jithinsankar]

Somebody please provide the pipeline!!

[nadia-metoui]

Joining the request for the pipeline Thanks!

[ak9250]

joining request as well, anyone been able to run the whole pipeline in google colab?

[matkir]

Joining

[FraGoTe]

any update on this?

[ldtuanAPCS]

Joining

[nirvitarka]

joining the request for full pipeline, @supasorn, thank you for sharing this work ,after 5 years of this original request raised, this repository is still one of the best approach to implement the lipsync, awaiting the remaining part from you now to see the real outcome of my training