Can the generated video improve MOT proformence

[cam-ai]

I saw in your paper, you said the generated image could improve 3D object detection task KPI, I checked your generated video, the generated car or other object, the consistency is not very well in image sequence, So I want to know, does the un-consistency issue decrease some MOT KPI if i use these generated video to enhance training dataset.

[flymin]

We haven't tried that yet, but we welcome any further improvements or reports.

[cam-ai]

Thanks for your reply.

[flymin]

FYI, our another work focusing on controllable video generation have tried to apply generated data for MOT training. You may want to take a look:

TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models https://arxiv.org/abs/2312.00651 https://github.com/pixeli99/TrackDiffusion

[cam-ai]

Thanks.