Comments (4)
I guess it should work if you find the right transformation to align to whatever metric prediction you have.
We plan it for the next release yes
from dust3r.
Hello @truncs and thanks for your interest!
Well in general, there is a problem to determine the scale of a scene with photogrammetry methods. Prior information must be leveraged as it cannot be guessed purely from triangulation. If you know the absolute depth of (at least one) view(s), or the scale of an object in the scene, you can use it to correct the output of our method, but this requires manual post-processing and is not part of our default pipeline.
Note that while DUSt3R does not output absolute metric reconstructions, it is theoretically possible to train it to do so, provided the training data is metric. We verified it in our experiments, but an absolute metric DUSt3R is still to be trained and evaluated properly.
from dust3r.
@vincent-leroy Thanks for the prompt reply!
Would it work if get the matched sampled points from stereo images with known baseline?
Are there plans to train a metric DUSt3R and release it?
from dust3r.
Thanks!
from dust3r.
Related Issues (20)
- The size of the point cloud does not match the actual size
- random crop generating more focals?
- Non-Interactive Demo? HOT 3
- Units of 3D point outputs from dust3r
- Is it possible to provide rough initial camera positions to Dust3R and get the finetuned accurate camera poses from it?
- An error occurred when entering the existing camera parameters for calculation HOT 2
- How to modify min_conf_thr in simple code HOT 2
- SegFault running the readme example
- The point cloud result obtained by inputting known camera pose and intrinsic parameters is incorrect in shape HOT 3
- About depthmap when training HOT 1
- We have removed the checkpoints temporarily
- About pretrained model when training HOT 1
- When will the checkpoint be avaliable? HOT 1
- WSL problem to set up docker
- About center point when training HOT 1
- MASt3R Demo & Initial Code Release Date HOT 1
- About training command and train_loss, val_loss HOT 6
- Where to Obtain Precomputed Pairs HOT 2
- Releasing MAST3R HOT 1
- Convert dust3er output poses to pytorch3d
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 dust3r.