Max Zhaoshuo Li 李赵硕

Hi @altava-sgp Could you see if you can reproduce reasonable results with the [colab](https://colab.research.google.com/drive/13u8DX9BNzQwiyPPCB7_4DbSxiQ5-_nGF)?

Hi @GuangyuWang99 Thanks for reporting. The information is very helpful. This looks like there is something fishy about the `trainer.test()`. Could you confirm that the **last saved checkpoint** performs as...

Hi @GuangyuWang99 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.

The tanks and temples preprocessing script has been updated (see https://github.com/NVlabs/neuralangelo/commit/54172deb11660fd6c64d727e600f0201b002347a) to fix the above bug and reflect the latest changes of data preprocessing.

Hi @Lionhk11 The installation README for AMBF missed `sudo apt install libgl1-mesa-dev xorg-dev`. Have you tried this?

@adnanmunawar Do you mind reviewing?

Hi @Magicboomliu Thanks for your interest. The occlusion mask can be obtained by finding the disparities that are out of range (i.e., leads to negative image index after warpping to...

Hi @lyfadvance Thank you for your interest in the project. The result indeed looks odd. Have you checked the logged accuracy? My side returns `Index 46, l1_raw 0.1737, rr 0.5591,...

Hi @xgyutu Thank you for your interest in the work! There is some guidelines in [the first Q&A](https://github.com/mli0603/stereo-transformer#common-qa). Could you see if these are helpful?

Hi @suriya030 and @18370271993 Sorry for the late response. Was the instruction in [this link](https://github.com/mli0603/stereo-transformer#data-structure) not helpful? The folder structure should be intact after downloading the KITTI data as follows:...