Comments (6)
@vvvsice Good question.
It's true that depths around the points are not same. The key idea is to compare patch similarity between different frames. You can also implement this idea in different manner. For example, first project 3D points to different frames and crop a patch around the projected coordinate then calculate the loss. However, this implementation ignore camera rotation while assuming same depth accounts for camera rotation.
from indoor-sfmlearner.
I see, thanks a lot.
from indoor-sfmlearner.
@vvvsice Good question.
It's true that depths around the points are not same. The key idea is to compare patch similarity between different frames. You can also implement this idea in different manner. For example, first project 3D points to different frames and crop a patch around the projected coordinate then calculate the loss. However, this implementation ignore camera rotation while assuming same depth accounts for camera rotation.
Hi,thanks for sharing this excellent work.
Could you please explain "this implementation ignore camera rotation while assuming same depth accounts for camera rotation" in more detail? I'm still confused about this.
Much appreciate.
from indoor-sfmlearner.
@belkahorry For the first one, you always crop a local patch around the projected point. The patch is a regular grid and not dependent on the camera rotation. For the second one, we project a patch (instead of point) with same depth to the other image and the projected patch is not a regular grid anymore and thus depends on camera rotation.
from indoor-sfmlearner.
It's clear,thanks!
from indoor-sfmlearner.
Hi, I'm still a bit confused as to why the regular grid would have a connection to the camera rotation.
from indoor-sfmlearner.
Related Issues (19)
- Fail to undistort images
- FileNotFoundError: [Errno 2] No such file or directory: '/home/agent/nyu_dataset/nyu_depth_v2/bedroom_0076b/r-1315244969.851995-2619100169.ppm' HOT 2
- hello, can you release the offline model? HOT 1
- multi scale question HOT 1
- Is this a typo? HOT 1
- inconsistent sampling methods during training and testing HOT 3
- Two questions about the dataloader HOT 3
- About monodepth2 result in the paper HOT 25
- shocked by the initial val result HOT 21
- 关于测试集与DeepV2D中测试集图片存在差异的问题
- nyu2 raw dataset does not match the split HOT 1
- NYUv2 dataset
- have you test on kitti? HOT 1
- Planar parameters are not actually calculated. HOT 5
- collapse issues when training HOT 3
- Keypoints extraction HOT 3
- 关于得到的深度图像的颜色和深度的对应关系 HOT 1
- pretrained model HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from indoor-sfmlearner.