Open littlepure2333 opened 1 month ago
Hi, yes, all three checkpoints were updated in June. We made some changes to the training recipe (we swapped one dataset for another).
Thanks for your prompt reply. May I know which dataset is swapped?
@littlepure2333 Hi, do you know the depthmap is metric depth or relative depth? Thank you!
@puyiwen In Dust3r, it's scale-invariant depth. If you want metric depth, you can check out Mast3r.
@littlepure2333 Thank you for your reply! Do you run the Linear head model? I found that the Linear head seems to get metric depth, while the DPT head gets relative depth.
@puyiwen Sorry I didn't run the liner head model. But since the training data is normalized in dust3r, all output depth of different dust3r variant should be scale-invariant.
Hi, thanks for your amazing work. However, I have a question. I ran the same inference code on the same image once in May and once yesterday, but I got quite different results (for example, depth). I'm wondering if you have updated the pretrained model weights (DUSt3R_ViTLarge_BaseDecoder_512_dpt)?
Image:
Before:
After: