DCVC-FM model is only applicable to datasets converted using the BT.709 standard under RGB test conditions?

Thank you for the released codes and models; they have significantly helped my research! However, I have encountered some confusion during the evaluation.

Most previous approaches have adopted PNG datasets extracted using ffmpeg software during the conversion from YUV420P to PNG. I tested both the DCVC-DC and DCVC-FM models on these datasets that were converted with ffmpeg. It was observed that the DCVC-FM model performed significantly worse under the same Group of Pictures (GOP) length of 32 in RGB test conditions, with the exception of the HEVC Class E dataset.

Has anyone else encountered this issue?

I conjecture the reason maybe that neural networks are easily fitted to data processing during training, considering that the training color conversion adheres to the BT.709 standard. However, traditional codecs perform consistently across different color conversion approaches.

No file, test, or entry point is identified in the issue. Start by reproducing the DCVC-FM and DCVC-DC comparison on ffmpeg-converted YUV420P-to-PNG datasets under RGB conditions, then establish whether the result depends on BT.709 conversion and document the confirmed evaluation behavior.