Comments (6)
Hi, I'm assuming you're running the code for 2D-3D feature matching here.
We use the cost volume to compute an expected 3d match, instead of using each matching hypothesis individually. This corresponds to eq (15) in the paper.
The expected 3D match is saved in tmp/match_line_pred.obj
. That should look reasonable, if it doesn't please let me know.
from banmo.
Hi,
My question is about the feature matching distribution (prob_vol in code) as shown in the following in Eq.15,
As I understand, when we can learn a good matching between 2d and 3d embeddings, this matrix should tend to have a dominant element in each row and each column. However, when I try to print it in the code, all elements are very close. So I am very confused about that.
from banmo.
This is not expected. Here is what I got:
slice=prob_vol[100].cpu().numpy()
print(-np.sort(-slice)[:10]) # largest 10 values
print(-np.sort(-slice)[-10:]) # smallest 10 values
array([0.01693168, 0.01188052, 0.01177971, 0.01088822, 0.01021699,
0.00911641, 0.00887904, 0.00791583, 0.00762484, 0.00664771],
dtype=float32)
array([5.4839586e-14, 5.3232704e-14, 2.3381782e-14, 9.0445856e-15,
7.8698915e-15, 6.0068172e-15, 3.0369735e-15, 2.0125922e-15,
2.2763142e-16, 2.2049661e-17], dtype=float32)
If you give more details of what data / command you use, I can take a further look.
from banmo.
Hi,
I run the template.sh on AMA-female data and print the matrix during training. The results are sometimes very close and sometimes very similar to yours.
When close, the biggest number is about 10^-4, and the smallest number is about 10^-5.
from banmo.
It could be that sometimes the sampled pixel happened to be belonging to the background, in which case, you may see a flat matching distribution.
from banmo.
Thanks for your reply!!!
from banmo.
Related Issues (20)
- Could you provide a demo that can work with one-click HOT 1
- Running out of space when running AMA (Samba + Swing) HOT 2
- Questions about the code. HOT 2
- Mesh generated on AMA-swing and Eval code HOT 2
- About projecting 3D verteces to 2D images HOT 1
- Error when rendering AMA-swing dataset HOT 2
- unable to load materials from: ./wood.obj.mtl HOT 3
- nvs_iter.sh HOT 2
- Extracting root pose HOT 1
- Loading the ".npy" files such as "cat-pikachiu.npy" or "shiba-haru-1.npy" has been failed HOT 3
- Questions about output results HOT 8
- exporting 3D models with skinning HOT 5
- Can Banmo support torch 1.11+cu113? HOT 1
- BANMo VS. ViSER HOT 2
- Clarification of the Matching Loss HOT 3
- Ckpt Release HOT 1
- face_normals all zero,ignoring
- The problem of extracting masks for deformable dynamic target objects HOT 3
- Enhancing Mesh Quality and Texture in BANMo Extracted Models HOT 1
- Questions about PoseNet HOT 4
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 banmo.