Open cv-lab-x opened 10 months ago
unofficial answer, maybe wrong: I tried different ablations, and some my new ideas(flat single gauss point and flat cloud gausspointS).
Isotropic vs. Anisotropic
I initilized the components in 'scale' with fixed same value, and disable the optimized/grad, the rotation is meaningless, or dynamic same value to keep scaling, in python.
of course, we can hardcode 'disable scale/rot' in cpp/cuda.
FYI.
unofficial answer, maybe wrong: I tried different ablations, and some my new ideas(flat single gauss point and flat cloud gausspointS).
Isotropic vs. Anisotropic I initilized the components in 'scale' with fixed same value, and disable the optimized/grad, the rotation is meaningless, or dynamic same value to keep scaling, in python. of course, we can hardcode 'disable scale/rot' in cpp/cuda. FYI.
hi,how to let each gaussian to learn same scale,instead of to fix their scale?like your "dynamic same value". I would be grateful if you could give me some advices. @yuedajiong
@dhuwzj 1) i dont think same scales can get better performance. 2) if you just want to 'try', too many methods: a) modify code: scale: vector_3 to vector_1, ellipse to spheree b) simpler code: vector_3 / 3 as real_scale_1, simpler, no renderer code change. ...
.repeat(1, 3)
on this line (so that self._scaling
is a (N, 1) tensor)
https://github.com/graphdeco-inria/gaussian-splatting/blob/2eee0e26d2d5fd00ec462df47752223952f6bf4e/scene/gaussian_model.py#L135.repeat(1, 3)
to the end of this line
https://github.com/graphdeco-inria/gaussian-splatting/blob/2eee0e26d2d5fd00ec462df47752223952f6bf4e/scene/gaussian_model.py#L97in this way the scaling is expanded to (N, 3) where the 3 scales are always the same (a repeated value of the self._scaling
parameter) no matter how you optimize.
@dhuwzj
- i dont think same scales can get better performance.
- if you just want to 'try', too many methods: a) modify code: scale: vector_3 to vector_1, ellipse to spheree b) simpler code: vector_3 / 3 as real_scale_1, simpler, no renderer code change. ...
Thanks for your reply, I'll try it!
omment
- remove the
.repeat(1, 3)
on this line (so thatself._scaling
is a (N, 1) tensor) https://github.com/graphdeco-inria/gaussian-splatting/blob/2eee0e26d2d5fd00ec462df47752223952f6bf4e/scene/gaussian_model.py#L135- add
.repeat(1, 3)
to the end of this line https://github.com/graphdeco-inria/gaussian-splatting/blob/2eee0e26d2d5fd00ec462df47752223952f6bf4e/scene/gaussian_model.py#L97in this way the scaling is expanded to (N, 3) where the 3 scales are always the same (a repeated value of the
self._scaling
parameter) no matter how you optimize.
Thanks for the code suggestion, I'll try it! Also thank you for the video explaining the 3d Gaussian CUDA code! 謝謝葵大!
hi, thanks for your great work, how to eval Isotropic mode in the code, reproduced the Ablations results in your paper ? looking forward to your reply, thanks! @Snosixtyboo