dhruvmetha

Results 7 comments of dhruvmetha

Fitting the RAFT model 16GB model on 2080Ti?

Thanks for the response! Will the code for this adaptation for RGB-D input be released? If not, could you give a high-level overview of how I could go about it,...

Fitting the RAFT model 16GB model on 2080Ti?

Thank you! It is mentioned you retrain on 3 datasets, Sintel, FlyingThings3D, and Monkaa. Do you do them in order and successively train for 100k, 100k and 100k iterations? Sorry...

Fitting the RAFT model 16GB model on 2080Ti?

Do y'all freeze the backbone post training on FlyingThings3D or just freeze the batchnorm inside the backbone model as done so in the original RAFT paper? Also do you use...

Fitting the RAFT model 16GB model on 2080Ti?

Thanks, this has been really helpful @wenbin-lin !

Fitting the RAFT model 16GB model on 2080Ti?

Is the equation from disparity to depth `depth = (focal_length * baseline) / (image_width * disparity)`, which is equivalent to `(1050 * 1.0) / (960 * disparity) ` for FlyingThings3D?...

Fitting the RAFT model 16GB model on 2080Ti?

Thank you @wenbin-lin

Fitting the RAFT model 16GB model on 2080Ti?

Do y'all have any rough evaluation results for optical training through each phase of training? This would really help me know if I'm training the model correctly!