Fix inference crash and dark rendering output

[nandometzger]

• Fixed TypeError in load_ply by converting numpy array to tensor before calling sRGB2linearRGB
• Fixed dark rendering issue by ensuring sRGB conversion is applied when input/output is sRGB (even if internal state is linear)

My testing file uses sRGB
I attach it here so you can reproduce the problem

Error message for the original code:

>>>sharp render -i output -o renderings
2025-12-18 13:38:15,124 | INFO | Rendering output/loki.ply
Traceback (most recent call last):
File "/scratch3/metzgern/random/ml-sharp/.venv/bin/sharp", line 8, in <module>
sys.exit(main_cli())
^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/.venv/lib/python3.11/site-packages/click/core.py", line 1462, in __call__
return self.main(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/.venv/lib/python3.11/site-packages/click/core.py", line 1383, in main
rv = self.invoke(ctx)
^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/.venv/lib/python3.11/site-packages/click/core.py", line 1850, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/.venv/lib/python3.11/site-packages/click/core.py", line 1246, in invoke
return ctx.invoke(self.callback, **ctx.params)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/.venv/lib/python3.11/site-packages/click/core.py", line 814, in invoke
return callback(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/src/sharp/cli/render.py", line 61, in render_cli
gaussians, metadata = load_ply(scene_path)
^^^^^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/src/sharp/utils/gaussians.py", line 326, in load_ply
colors = cs_utils.sRGB2linearRGB(colors)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/src/sharp/utils/color_space.py", line 52, in sRGB2linearRGB
return robust_where(
^^^^^^^^^^^^^
File "/scratch3/metzgern/random/ml-sharp/src/sharp/utils/robust.py", line 40, in robust_where
input_2 = torch.where(~condition, input_2, branch_false_safe_value)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: where() received an invalid combination of arguments - got (numpy.ndarray, numpy.ndarray, float), but expected one of:
* (Tensor condition)
* (Tensor condition, Tensor input, Tensor other, *, Tensor out = None)
* (Tensor condition, Number self, Tensor other)
didn't match because some of the arguments have invalid types: (numpy.ndarray, numpy.ndarray, float)
* (Tensor condition, Tensor input, Number other)
didn't match because some of the arguments have invalid types: (numpy.ndarray, numpy.ndarray, float)
* (Tensor condition, Number self, Number other)
didn't match because some of the arguments have invalid types: (numpy.ndarray, numpy.ndarray, float)

[domiverse]

thêm color render alias