Comments (2)
KopiSoftware
commented on June 30, 2024
I met similar problem and find that Atlas only produces results when meshes in the positive octant. Though I translated all the poses to positive octant, the results is still unacceptable. This situation is also occurred when I try to reconstruct models with NeuralRecon. They all use Scannet as dataset.
My pose data is collected from a one line lidar, or vins. The poses is aligned to image within 1ms error. I can rebuild model by tsdf fusion with my data.
So could anyone tell us how to pre process the pose data to fit Atlas?
from atlas.
bharath-07
commented on June 30, 2024
Running through the same issue, could someone clarify?
from atlas.
Related Issues (20)
- Error on running inference on the sample dataset HOT 3
- Train my own data HOT 4
- pip package version specification ">=" and redirection
- Inference With Latest COLMAP Broken
- GPU Memory Required for Inference HOT 1
- RTX 3060 HOT 5
- About inference.py HOT 2
- Protocol Buffer library not compatible HOT 3
- AtlasInference.ipynb throws FileNotFoundError HOT 1
- The meaning of Atlas
- AttributeError: can't set attribute HOT 1
- Ask about the dataset
- SyntaxError: invalid syntax" HOT 2
- Unable to open ply files HOT 2
- About the origin tensor in backproject function.
- Why not use ScanNet provided mesh as ground truth?
- Inference on custom dataset HOT 1
- Visualization of .ply or .npz
- How to display the feature volume HOT 1
- No access to pretrain resnet50 weigths 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 atlas.