Are there plans to open-source the training data augmentation code (4D Geometric Control pipeline)?

[zzezze]

According to the paper, starting from Sekai-Real-HQ and SpatialVID-HQ, 81-frame clips are extracted followed by quality filtering. For each retained clip, Qwen2.5-VL-72B, GroundedSAM2, and MegaSAM provide captions, object masks, depth, and camera poses, which are lifted into background/object point clouds, fitted with 3D Gaussian trajectories, and rendered as background/trajectory maps plus a merged mask that constitute the 4D Geometric Control.

Are there any plans to open-source the code related to this training data augmentation pipeline?

Looking forward to your response. Thank you!

[sixiaozheng]

Hello, thank you for your support of our work. We will be open-sourcing the training code and data processing code soon. However, unfortunately, due to company policy restrictions, we are currently unable to open-source the dataset.