Max Zhaoshuo Li 李赵硕

Hi @BoMingZhao @AuthorityWang I set the `checkpoint.save_iter` (the line below) to 2k so I can frequently inspect the results. I have not been able to reproduce the issue with early...

@BoMingZhao @AuthorityWang We have pushed a commit that potentially fixes the issue of resuming (https://github.com/NVlabs/neuralangelo/commit/c91af8d5098c858df8e8dfa35fba8666d314782b). Please let us know if you still run into the same problem. If the issue...

Hi @iam-machine Good to hear that you have found some interesting places to reconstruct :D Most of your intuitions are correct. - Note that when COLMAP undistorts the images, it...

Hi @iam-machine Based on the quality of normal maps, I would say the training fails to converge. It looks like the bounding box is fairly loose (not sure if it...

I am looking into potential bugs in the pipeline that may have also caused several other issues reported. I will update once confirmed.

That's very good insight @DerKleineLi!! Thanks for sharing! I would like to also add that the tutorial uses COLMAP to obtain the poses instead of using the GT poses. The...

Hi @maomaocun You can follow the README and use `--textured` to extract textured mesh.

Hi @Dangzheng @Runsong123 Thanks for reporting. We will look into this. A few quick comments: - We followed NeuralWarp's evaluation protocol. The details are described in Appendix D 3rd section...

Hi @xiemeilong Thanks for reporting this. This is indeed odd and unexpected. To narrow down the problem, could you help by providing the following information? - Do you use the...

Hi @Dragonkingpan The `scene_type` has two use cases: - Deciding the bounding box [here](https://github.com/NVlabs/neuralangelo/blob/f512b278768ec04fd89c78430dd80702971378b1/projects/neuralangelo/scripts/convert_data_to_json.py#L190). If the trajectory is similar to an object-centric scene, it will use the poses to bound...