Skip to content

question about DCVC_RT's BDrate against VTM-17.0 #96

Open

Description

Hello, i use your test suggest to calculate bdrate for DCVC_RT. But my result is far from yours, can you help me?
There are my encode commands:
DCVC_RT:

 python test_video.py 
 --model_path_i cvpr2025_image.pth.tar 
 --model_path_p cvpr2025_video.pth.tar 
--test_config dataset_config_example_yuv420.json 
--rate_num 10 --cuda 1 -w 4 --write_stream 1 --force_zero_thres 0.12 
--output_path dcvcrt_output.json 
--stream_path dcvcrt_out_bin
--force_intra_period -1 --reset_interval 64 --force_frame_num 96 
--check_existing 0 --verbose 2 verbose_json True --calc_ssim True 
--save_decoded_frame True --cuda_idx 4 5 6 7

VTM-17.0 and HM-16.25:

EncoderApp -c encoder_configuration.cfg 
-f 96 -q {qp} --IntraPeriod=-1 --InputFile={src_yuv} 
--SourceWidth={width} --SourceHeight={height} --FrameRate={frame_rate}
--Level=6.2 --InputBitDepth=8 --DecodingRefreshType=2 
-b {output.bin} -o {enc.yuv}

Then I calculate bdrate (use "ave_all_frame_bpp" and "ave_all_frame_psnr") for every seqs, then calculate their average, but the results are far from your paper's.

Image

I also plot the RD curves for every dataset, compare my RDcurve with your paper's RDcurve figures. But they don't fit perfectly(HEVC_C is far from your curve). For example:

UVG

HEVC_C

HEVC_E

I notice that your paper's RDcurve figures are all for a whole dataset, not for a single seq. So I also calculate BDrate for per dataset, results follow as:

Image
which are closer to your paper results, do you calculate bdrate in this way?
Could your answer my questions? Thanks for reading!

Activity

  1. yaohualibin commented on Apr 21, 2025

    @yaohualibin
    Contributor

    Table 2 reports the results for all frames in the sequence, but it seems that you only tested 96 frames, --force_frame_num 96 in your command.

  2. GabrielGao0310 commented on Apr 21, 2025

    @GabrielGao0310
    Author

    Table 2 reports the results for all frames in the sequence, but it seems that you only tested 96 frames, --force_frame_num 96 in your command.

    Yes! Because I have seen that your test_condition.md's suggestion:

    Image
    So table 2 are results for all frames in every sequence?

  3. yaohualibin commented on Apr 21, 2025

    @yaohualibin
    Contributor

    Yes, they are for all frames in every sequence (the exact number of frames are defined in the json file).

  4. GabrielGao0310 commented on Apr 21, 2025

    @GabrielGao0310
    Author

    Yes, they are for all frames in every sequence (the exact number of frames are defined in the json file).

    thanks, i will try again using all frames!

  5. GabrielGao0310 commented on Apr 21, 2025

    @GabrielGao0310
    Author

    Yes, they are for all frames in every sequence (the exact number of frames are defined in the json file).

    Could you please send me the RD curve datas for each sequence? I’d really appreciate it. My email: gabrielgao@sjtu.edu.cn

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions