Comments (8)
Thanks for your comments, @ychao-nvidia .
The paper did not mention that for For each test sample, you assume to have GT bounding box coordinates and camera intrinsic to report the absolute errors.
Regarding 100 mm absolute error, I did my experiments assuming that I do not have bounding boxes for test samples!
from dex-ycb-toolkit.
Hi @zc-alexfan
Do you have any idea about my question?
from dex-ycb-toolkit.
Sorry, I did not use it.
from dex-ycb-toolkit.
Hi @umariqb,
I would appreciate your comments on my issue.
from dex-ycb-toolkit.
Answers to your questions:
-
Yes, we followed [31] for the baselines reported in Tab. 7. Therefore, yes, the input to the network is a 128 x 128 RGB image cropped around the bounding box.
-
We report absolute error by computing the 3D distance between the ground-truth and predicted joint positions.
Two additional comments regarding [31] and absolute error:
-
[31] predicts a special "2.5D representation" (see [18]) for the hand pose, and then uses the bounding box coordinates and the camera intrinsics to convert this "2.5D representation" to the 3D pose. That said, the task of the network is only to predict (1) the 2D locations of keypoints within the input image and (2) the root-relative depths of keypoints (see [18]), which is reasonable for a cropped image input. With this "2.5D representation", converting to 3D pose is well-posed (see [18]).
-
With that said, the input for this benchmark (for RGB-only) should really be (1) the full RGB image, (2) the bounding box coordinates, and (3) the camera intrinsics---not just the cropped image itself. You can see [31] as using (1) and (2) to get the input of their network (i.e., the cropped image).
from dex-ycb-toolkit.
Hi @ychao-nvidia I'd like to compare my results on Dex YCB dataset to your results(Table 7, 3D hand pose estimation)
It seems ground truth bounding box for hand is not available in test time,
so what bounding box (maybe using 2D joints coordinates or detected bounding box ... ?) did you use when crop image for hand in test time ?
from dex-ycb-toolkit.
As mentioned above, for hand pose estimation we assume the bounding box is given at test time.
We calculated a tight bounding box by [min(X), min(Y), max(X), max(Y)]
, where X
(Y
) is the 2D x
(y
) coordinates of the 21 hand joints provided in the ground truths.
We then cropped a square image region (1) with a center shared with this tight bounding box and (2) with a side length of l
, where 0.7*l=max(w, h)
and w
and h
are the width and height of the tight bounding box. We used this cropped image region as the input to our network.
from dex-ycb-toolkit.
Thanks for clear comments!
from dex-ycb-toolkit.
Related Issues (20)
- hand pose, translatation and rotation parameters HOT 2
- the form of hand pose annotations HOT 8
- Trained weights of Mask R-CNN and SOLOv2
- Depth ambiguity for RGB only methods HOT 1
- Inconsistency in pose_y for per_image and per_sequence HOT 7
- How to obtain point cloud of object? HOT 1
- mano shape consistency for right and left hand. HOT 4
- Objects in the DEXYCB dataset HOT 1
- Does the dataset provide 3D object bbox? HOT 4
- ModuleNotFoundError: No module named 'utils.eval_util' while testing examples/evaluate_hpe.py HOT 2
- MANO pose coefficients (theta) HOT 5
- subject-specific hand shapes (ß) HOT 2
- World Frame Alignment HOT 1
- One more videos for class 2. HOT 1
- Question on teaser HOT 1
- pyglet 2.0.9 requires Python 3.8 or newer. HOT 2
- How to get absolute depth values for each pixel? HOT 3
- Banana point cloud looks flattened HOT 2
- Why y-axis and z-axis multiply by -1? HOT 2
- Camera extrinsics, intrinsics and depth 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 dex-ycb-toolkit.