Comments (3)
The script will save out inverse depth (which with a slight abuse of terminology refer to as "disparity" - to so convert to depth you can just do depth = 1 / disparity
.
However, since we have trained from monocular sequences only, our predictions will be in an arbitrary scale. To convert to real world scale you can apply the same median scaling that happens when we are evaluating the model on line 336
manydepth/manydepth/evaluate_depth.py
Line 336 in 28fbbcf
pred_depth
after line 339.
Let me know if that works for you.
from manydepth.
Hi, thanks for your interest in the repo!
Sure - to save the predicted disparities after evaluation you can add the --save_pred_disps
option to the command line, this should save out a block of predictions.
As for running on the benchmark data - I see the same error as you, and I actually see the same when trying to run using the Monodepth2 repo (on which Manydepth is based), so I will bring this up with the authors and see if we can get a push fixed.
Thanks a lot for finding this bug!
from manydepth.
Hi, thanks for your interest in the repo!
Sure - to save the predicted disparities after evaluation you can add the
--save_pred_disps
option to the command line, this should save out a block of predictions.As for running on the benchmark data - I see the same error as you, and I actually see the same when trying to run using the Monodepth2 repo (on which Manydepth is based), so I will bring this up with the authors and see if we can get a push fixed.
Thanks a lot for finding this bug!
Thanks for replying!
I've saved disparity map by this way. Is there any demo to convert disparity map to depth map in this repo?
from manydepth.
Related Issues (20)
- Training on NYU-V2 Dataset
- Stereo + Tempora (training with stereo video like monodepth2)
- About cityscapes disparity to depth_gt HOT 2
- Can the scale ambiguity be resolved with multi-frame approach? HOT 1
- Depth Estimation Results on Single Frames
- Question of relative pose in matching augmentation.
- how to test many frames at the same time?
- Help training out bright reflection... HOT 1
- About scale problem in monocular setting HOT 2
- Why the training time of manydepth is much shorter than monodepth2? HOT 3
- when i test the image,the result of the depth is black HOT 1
- About MAX gt_depth HOT 2
- Get gt depth for other Cityscape images HOT 2
- Calculate the gt depth for Cityscape images HOT 3
- About qualitative results presented in Figure 4 HOT 1
- The dataset GT-Calculation HOT 1
- what should the
- How to conduct multi GPU training
- On the pre training model of cityscapes HOT 3
- custom dataset prepare
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 manydepth.