isabella98liu / dg-mesh Goto Github PK

Hey Isabella,

Thanks for sharing the great work! Do you have any schedules to release the code? It would be great if you set an approximate time so we can stay tuned and follow up in time!

Thanks a lot !

You have done a great job. I have a question, how do you draw the red trajectories shown on the websites, any tool recommendations?

Hi, Thanks for the great work!

I was reading your work, and wondered how nvdiffrast can be actually implemented to render an image from a mesh that is being trained.

From my understanding, mesh from DPSR + Diff.MC during optimization can have varying number of vertices for every iteration.

In this case, how can a trainable color be defined for each vertex for every iteration?

Thank you in advance.

I am intrigued by the research presented in your paper. While going through the document, I observed that PSNR corresponding to mesh is provided in Table.1, but there seems to be a missing entry for Gaussian. From my understanding, mesh and Gaussian have a one-to-one correspondence and can be independently rendered to generate images. I was wondering if the authors could kindly explain why Gaussian's PSNR data is not included in the table. This information would be valuable for evaluating the method's performance and making comparisons. Any clarification on this matter would be greatly appreciated.

Hi, I'm very interested in your work. I found that DPSR uses a regular grid for obtaining SDF. It seems a high grid resolution leads to better mesh details. I wonder about the resolution parameter of work. Thank you!