unimatch
unimatch copied to clipboard
[TPAMI'23] Unifying Flow, Stereo and Depth Estimation
Impact of Iteration Discrepancy Between Supervised and Unimatch Models on Optimization and Results
In the Unimatch code, I've observed that the 'self.ids' of labeled data are extended to match the length of the unlabeled data. Consequently, within the same epoch, the number of...
This PR adds types to function signatures to be able to use `torch.jit` or `torch.onnx.export()`. I also had to convert some functions to modules The code should be equivalent to...
perfect work guys,and,do you plan to make a live camera estimation?maybe with gui window
I follow the other issues and install COLORMAP to run python imgs2poses.py ../scenedir3/ and sussess. then I got sparse folder with have some *bin file and some *txt *db *npy...
I have images from different cameras with different intrinsics that I would like the calculate the depth from. I already have the intrinsics for each and the relative pose between...
Hi, I try to export your model to onnx. Did you try to do something like this? Now I`m stuck with "RuntimeError: Expected a sequence type, but received a non-iterable...
Hi, Would you be interested in incorporating unimatch into kornia library? We have sota image matching like LoFTR and now are looking for some good optical flow & stereo method....
Hi authors, thanks for sharing this great work! Have you also tested the model (in particular the flow model) with FP16 or mixed precision (AMP)? If so, how does the...
Thanks for your excellent work! After saw your code in unimatch.py, I got a little bit confused about line 160 and the following warping part. I want to know why...