Open PedestrianZQZ opened 3 years ago
Hi. I'm not sure I can help you on HDR10 specific questions, and it depends on which container is used for the HDR video. You would have to look into the codec specification. For the HDR videos we used in training, each frame was provided as a separate EXR image.
Thanks for your reply! The format of video is unlimited, i have .mp4 now, but i think it is easy to transform into .mkv, which you have mentioned in other issue. I just want to know the whole route that you finally got separate EXR images.
I did not need to extract frames from a video, they were already provided as separate EXR images.
I have done some work on encoding and decoding HDR video: https://github.com/gabrieleilertsen/lumahdrv
However, it was some time ago, so I don't think I'm very helpful. Also, you can most probably extract frames much easier than this.
I see. thank you very much
@PedestrianZQZ Did you figure out a way to do this?
hi, thanks for sharing your outstanding work!
now I'm going to train a model to perform reconstruction from SDR video to HDR video. I've got some HDR10+ video, could you please tell me how to extract frame from it losslessly? You mentioned that use every 10th frame in the video, I wonder how you made it?