Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
I want to merge the MiDaS pretrained model into my bundle adjustment system. However, my model constrained large size image input as 384x224. I am thinking about which pretrained model is best for me? Can I use dpt_beit_large_512 pretrained model in my case?
I want to merge the MiDaS pretrained model into my bundle adjustment system. However, my model constrained large size image input as 384x224. I am thinking about which pretrained model is best for me? Can I use dpt_beit_large_512 pretrained model in my case?