Alex Wong

You can follow the general instructions in this thread of our recent work KBNet: https://github.com/alexklwong/calibrated-backprojection-network/issues/17#issuecomment-1176431551 This repo is in Tensorflow so it is a bit harder to use for the...

Hello, thank you for your interest, we measured the absolute trajectory error, relative pose error and relative rotation error Their definitions were included in our supplementary materials. As we progress...

Hello, you can use the pose evaluation metrics inside src/eval_utils.py, please see https://github.com/alexklwong/unsupervised-depth-completion-visual-inertial-odometry/commit/12d8beb280bbc5cea8512f2b9c74e21c4db930b0.

Hi, sorry that was an old run script that seemed to have survived the code clean up. Can you try using https://github.com/alexklwong/calibrated-backprojection-network/blob/master/bash/void/run_kbnet_nyu_v2.sh instead? I will delete https://github.com/alexklwong/calibrated-backprojection-network/blob/master/bash/void/run_knet_nyu_v2_test.sh

Sorry I’m in Tel Aviv for ECCV this week so replies may be slow. Let me set up the repo and try.

This is quite strange. I setup the repo from scratch and ran the void-1500 checkpoint on VOID1500 and NYUv2 test sets: For VOID1500 ``` Evaluation results: MAE RMSE iMAE iRMSE...

Hi, looks like there are some issues with torch version and CUDA affecting training and inference. Previously, it was done with GTX family. We are now retraining on RTX with...

Hi, yes we do have plans to do this. While I am a firm believer in continuing to support and serve the community with this work, our group does have...

Hi, it has been a while so I don't recall all the details. My impression was that we used the factory calibration settings and directly read from the RealSense through...

Hi, in short, it depends on the format of your depth maps. Typically, depth maps are stored as PNGs as in accordance with the VOID and KITTI datasets. To preserve...