Rui Zhu

> @pengwangucla @XibinSong Hi, Yes. I think the mesh problem is solved. However, there is a new issue in term of using camera intrinsic in the code. > I have...

Hey Hang, thanks for the comment! Additionally I am wondering if you have any statistics on how big the performance gap is between native and functional implementations, especially in case...

Ah i see. Thanks! The native version would also be useful for prototyping because it is easier to build upon.

Hey Hang, after a second thought, the original version is actually correct to me. `kernel` will be used when you compute `grad_input`, and `input` will be used when you compute...

@Guodonggogo Yep. The code for the full scale estimation will be uploaded soon (hopefully within two weeks). Thanks for your patience!

> it seems that debugging module is not uploaded? Hey Guodong, the repo has just been updated with demo of inference and virtual object insertion using the ScaleNet on COCO...

@grainw Hey Alex, sorry for late release of the training part. If you need the code for ICCV or other pending deadlines I can try to find some time to...

> Hey @kevinj22 thanks for pointing towards the conversion to .tif! However I wonder if you can further point out how to convert from .tif to .exr (in Python or...

> Thank you very much! I am currently working on adding support for semantic segmentation training and inference in this repository, once we have this enabled it should be easy...

Same issue here. Using a ESP32-S@ board + TSL2591 light sensor here, flashed with firmware from [here](https://lunar.fyi/sensor). Here is the log. I really appreciate it if you could please help...