Questions Regarding Image Resolution, Camera Intrinsics, and Frame Rates

Hi, thank you for your excellent work.

I noticed that the released dataset appears to be a subset of **MVHumanNet**, but the image resolution is **1024 × 1024**, which seems to differ from the resolution described in the original paper.

Could you please clarify the following points?

1. How should the original images be resized and/or cropped to obtain the target resolution of **1024 × 1024**?
2. Have the corresponding camera intrinsics been adjusted to account for the resizing and cropping operations?
3. Regarding the frame rates, is the data organized as follows?
- **25/25=1 FPS** for IDs beginning with `10****`
- **30/25=1.2 FPS** for IDs beginning with `20****`

Thank you in advance for your clarification.

Compare the released MVHumanNet++ dataset with the original MVHumanNet paper, focusing on the 1024 × 1024 image preparation, camera intrinsics, and frame-rate organization for 10**** and 20**** IDs. Done means providing authoritative clarification for all three questions; the payload names no repository files or tests.

Written by the indexing model from the issue text.