Comments (4)
Hi,
You can take a look here for how depth is computed from our predicted scaled disparity:
https://github.com/nianticlabs/monodepth2/blob/master/evaluate_depth.py
Roughly speaking, to compute real-world depth from the network prediction:
output = depth_decoder(encoder(input_color))
pred_disp, _ = disp_to_depth(output[("disp", 0)], 0.1, 100)
pred_depth = 5.4 / pred_disp
(But all of @mrharicot 's caveats remain about focal length and image size and ratios etc)
from monodepth2.
Hi,
There isn't a good answer for this I am afraid.
The network was trained for a specific focal and image ratio. If we evaluate on a different ratio and focal we can't really predict what the network will do.
You can start by assuming that the network will predict the same scale as on KITTI which for our models trained with stereo supervision is 5.4
from monodepth2.
Thanks for reply Can you tell what do mean that stereo supervision is 5.4 and also can you provide the camera configuration or kitti config like focal ,ratio
from monodepth2.
Thanks
from monodepth2.
Related Issues (20)
- Network inference time problem
- The requested array has an inhomogeneous shape after 1 dimensions. HOT 5
- Write split file HOT 2
- obtained some very strange depth maps HOT 4
- The difference in the intrinsic matrix affects the results
- Question about image resolution
- question for the Data Preparation
- Why is smooth_loss divided by 2**scale?
- Questions about the meaning of grid in the F.grid_sample function
- the eval file about 'gt_depths.npz'
- Run on Google Colab,
- Run on Google Colab, but out of System RAM
- The new constraint about pose is not useful?
- RuntimeError: CuDNN error: CUDNN_STATUS_SUCCESS HOT 2
- How to obtain reconstructed image and loss for a single demo image
- How to setup already trained computer vision model Ultralytics YOLOv8 with monodepth2 HOT 1
- Questions about pose estimation HOT 1
- Different evaluation criteria for Monodepth2 M and S
- Regarding the patent and license HOT 1
- RuntimeError: The size of tensor a (319) must match the size of tensor b (639) at non-singleton dimension 3
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 monodepth2.