vt-vl-lab / 3d-photo-inpainting

[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
https://shihmengli.github.io/3D-Photo-Inpainting/
Other
6.88k stars 1.11k forks source link

Video generation process stuck in 3D-photo-inpainting #203

Open ookidayone opened 1 year ago

ookidayone commented 1 year ago

Hello everyone,

I have been using the 3D-photo-inpainting project to generate videos from still images. However, I have encountered an issue where the video generation process seems to be stuck at the "Making video" stage. I have tried running the process multiple times, but the result is always the same. The GPU usage remains low, indicating that the process might not be progressing.

Here is the output log from the script:

finished
Start Running 3D_Photo ...
Loading edge model at 1683207961.8534467
Loading depth model at 1683207962.2114456
Loading rgb model at 1683207963.0374477
Writing depth ply (and basically doing everything) at 1683207963.817446
Writing mesh file 3d-photo-inpainting/mesh\1.ply ...
Making video at 1683208142.5625007

I have tried restarting the script, updating the program and libraries, freeing up memory, and adjusting the input data size and resolution, but the issue persists. I would appreciate any suggestions or insights from the community to help me resolve this problem.

Thank you in advance for your assistance.

Best regards,