Cheol-Hui Min

Thanks for this awesome reimplementation! It really gave me a good intuition for adapting the paper for my work. I agree with @dbsxdbsx for the weighting term in the continuous...

Oh, now I get the implementation. I think the implementation of @nisheeth-golakiya is correct. The `prob_d ` or `p_d ` term inside the parenthesis is the weighting term used for...

Thanks for the clarification. I'll delve into the kl div minimization view of algorithm soon.

@dbsxdbsx Oh, your point seems convincing. I also found a work that formulates hybrid-sac very similar to this paper, and it has official code implementation. In this implementation, the formulation...

I faced the same problem, and this line yields the error https://github.com/NVIDIAGameWorks/kaolin/blob/b6cf8073edbe9b5469f643d3b9cf57b0f43651db/kaolin/render/easy_render/mesh.py#L106 I modified this to ``` im_base_normals = im_base_normals * im_normal_sign.unsqueeze(-1) ```, and it resolved the problem @shumash