search

justimyhxu / GRM

Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation
https://justimyhxu.github.io/projects/grm/
499 stars 27 forks source link

Sparse-view reconstruction #8

Open YSYYU opened 3 months ago

YSYYU commented 3 months ago

Thank you for your excellent work! From your paper, I can see that there is still a section on sparse-view reconstruction. Where is the code for this section?

justimyhxu commented 3 months ago

We don't provide a test example for sparse-view reconstruciton. But you can refer this function https://github.com/justimyhxu/GRM/blob/4cd9c3930249b7d708d27d98bb6ea7dc12c8e0df/test.py#L219 to setup your input images and poses for reconstruction.

YSYYU commented 3 months ago

ok, thank you for your reply! May I ask which areas should be changed?

justimyhxu commented 3 months ago

You can refer this code block to set up your image and camera pose inputs. https://github.com/justimyhxu/GRM/blob/4cd9c3930249b7d708d27d98bb6ea7dc12c8e0df/test.py#L453

YSYYU commented 2 months ago

Thanks your reply. So what do the parameters r=2.7 and pose [20, 225+30] represent respectively, and how are these parameters determined？