Apeiria

> Hi @Apeiria , > > Thank you for reporting. > ScalableTSDF uses the unordered_map implemented in STDGPU, but it is not very memory efficient. > I am currently exploring...

Hi, I notice that you use `float` for tsdf value and weight, `Vector3i` for index, and `Vector3f` for color. So it takes 32 bytes per `TSDFVoxel`, and a 512^3 volume...

> Hi, > I notice that you use `float` for tsdf value and weight, `Vector3i` for index, and `Vector3f` for color. So it takes 32 bytes per `TSDFVoxel`, and a...

> This is usually caused by GPUs going to idle and not an issue in TRT. Could you check the solution in #2042 and see if it works? Thanks for...

> No, it's mostly caused by the GPU driver, so you need to change the driver settings. OK, thanks a lot for your help!

> No, it's mostly caused by the GPU driver, so you need to change the driver settings. Hi again, I just did the same experiment in pytorch, and I found...

> @Apeiria Is the PyTorch using GPU or CPU? Also, could you try `time.sleep(5)` and see if it makes any difference? My pytorch is using gpu. I tried time.sleep(5) and...

> interesting... we will take a look when having the chance. Meanwhile, I still recommend that you try the approaches in #2042 to see if any of them fixes the...

语气这么牛逼，作者求着你用了？

> Hi, @Apeiria > > Thank you for your question. > We are actually using `Center-Symmetric Census Transform`. > It compares only center-symmetric pairs of pixels. > > For more...