Questions About Metric 3D Reconstruction, Dynamic Scenes, and High-Res Image Processing

Dear authors,
Thank you so much for your excellent work! I have a few questions regarding the model's capabilities:
Does it support metric 3D reconstruction with multi-view inputs, such as the surround-view images from the Waymo dataset?
Does it support 3D reconstruction for dynamic scenes? If not, is the alternative to treat each frame of a dynamic scene as a static scene for reconstruction?
For high-resolution images, scaling often leads to significant information loss. Is it feasible to crop a single high-resolution image into a set of smaller images as multi-view inputs, then stitch their generated pointmaps to form a complete scene?
Looking forward to your reply!