cvg / nice-slam

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Home Page:https://pengsongyou.github.io/nice-slam

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about pre-filtering rays out of bounding box

heyicheng-never opened this issue · comments

Thanks for your work!
On line 474 in Mapper.py:
t = (self.bound.unsqueeze(0).to( device)-det_rays_o)/det_rays_d t, _ = torch.min(torch.max(t, dim=2)[0], dim=1) inside_mask = t >= batch_gt_depth
I can't understand the meaning of this code. Can you help explain it? Thanks!

Hey, these two lines perform ray-bounding box intersection.

got it. Thanks!