taichi_3d_gaussian_splatting

taichi_3d_gaussian_splatting copied to clipboard

simply training.

56

wanmeihuali

Backward formula

20

wanmeihuali

How to improve result?

4

Hello @wanmeihuali , I have started doing some experiments with the code. The implementation is really good and clean, I like it. I have couple of questions regarding result quality....

hardikdava

working with 32bit or 16 bit floating point images for ACES color managed workflow.

2

As far as I can understand this implementation uses only 8bit images as input. Would it be possible to take linear EXR or similar formats to preserve more data from...

luuude

'use default_factory' error on python 3.11

1

Hi, when I tried to run this initially I got the following error: ``` [Taichi] version 1.6.0, llvm 15.0.4, commit f1c6fbbd, linux, python 3.11.5 Traceback (most recent call last): File...

expenses

IndexError: tensors used as indices must be long, byte or bool tensors

2

```bash [Taichi] version 1.6.0, llvm 15.0.4, commit f1c6fbbd, linux, python 3.9.18 [Taichi] Starting on arch=cuda 0%| | 0/30001 [00:00

StarsTesla

parquet_view

1

Can you help me to make the file.parquet transform to file.obj,or can you make the file.parquet transform to other file 3D

haung-hangdian

Error running prepare_colmap.py

1

Error running prepare_colmap.py, any ideas? ``` (3, 191076) (3, 191076) Traceback (most recent call last): File "D:\.repos\taichi_3d_gaussian_splatting\tools\prepare_colmap.py", line 275, in 'camera_intrinsics': camera['K'].tolist(), AttributeError: 'NoneType' object has no attribute 'tolist' ```...

henrypearce4D

Question on gradient of depth

16

Thanks for the great work! This work is awesome. I note that the gradient is not backpropaged from the pred_depth, do you plan to add it? This would be super...

chenyuntc

Test depth grad on xyz and alpha. Note: I found the initialization of alpha is important: 1. To optimize the alpha: if there are too many points, the initial alpha...

chenyuntc