Hello, I am very envious of your team for such wonderful work. When I was training the model, I found that the dataset part of this code directly transforms a picture according to the maximum angle of 45 degrees and then inputs it into the model? Then I now need to train a model that can adapt to large angles. I hope you can give me some ideas.Thank you.
Thank you! Indeed, the model pretrained on homographies is also more robust to rotations. You could try to add homography adaptation to MegaDepth and see if this translates there.
Hello, I am very envious of your team for such wonderful work. When I was training the model, I found that the dataset part of this code directly transforms a picture according to the maximum angle of 45 degrees and then inputs it into the model? Then I now need to train a model that can adapt to large angles. I hope you can give me some ideas.Thank you.