Xharlie / DISN

(latest updates and bug fixed) DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction
183 stars 27 forks source link

Am I doing something wrong? #7

Closed edoRemelli closed 4 years ago

edoRemelli commented 4 years ago

Thanks for the sharing this with the community!

Should we except a slight misalignment between sdfs in "sdf_dir" and marching cube reconstructed ground truth models in "norm_mesh_dir"?

If I project sdf surface samples (obtained as np.abs(pc_sdf_sample[:,3])<0.005) and mesh vertices on the renders using trans_mat = np.linalg.multi_dot([K, RT, rot_mat, W2O_mat, norm_mat]) I notice a slight misalignment for the mesh vertices (see second attached screenshot).

Is this expected, or am I missing out something? Thanks!!

image

image

bharadwajdhornala commented 4 years ago

Hi @edoRemelli Could you help me solve Issue #6 ? Thanks!!

Xharlie commented 4 years ago

we will actively look at this, does it happen to all the models?