Trance-0/NoteNextra-origin
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

fix typo and add images

Browse Source
This commit is contained in:
Trance-0
2025-09-03 22:27:42 -05:00
parent 9b98f1e4b1
commit ea138d56b8
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
content/CSE5519/CSE5519_E1.md
View File

@@ -318,7 +318,7 @@ $$
p_s\sim K\hat{T}_{t\to s}\hat{D}_t(p_t)K^{-1}p_t p_s\sim K\hat{T}_{t\to s}\hat{D}_t(p_t)K^{-1}p_t
$$ $$
The we use spacial transformer network to sample continuous pixel coordinates. Then we use spacial transformer network to sample continuous pixel coordinates.
### Compensation for PoseNet & DepthNet ### Compensation for PoseNet & DepthNet
@@ -336,7 +336,7 @@ Since it's inevitable that there are some moving objects or occlusions between t
This is a method that use pair of images as Left and Right eye to estimate depth. Increased consistency by flipping the right-left relation. This is a method that use pair of images as Left and Right eye to estimate depth. Increased consistency by flipping the right-left relation.
**Intuition:** Given a calibarated pair of binocular cameras, if we cna learn a function that is able to reconstruct one image from the other, then we have learned something about the depth of the scene. **Intuition:** Given a calibarated pair of binocular cameras, if we can learn a function that is able to reconstruct one image from the other, then we have learned something about the depth of the scene.
### DispNet and Scene flow ### DispNet and Scene flow

BIN
public/CSE5519/Left-right_consistency_Network.png.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 68 KiB