Comments (2)
Hi @zehongs , I am sorry for the delayed response. In the new version of the paper, we will update global metrics with more comprehensive and globally used ones including normalized root-translation error (RTE), foot sliding (FS), and jitter. Following this, we will update the lib/eval/evaluate_emdb.py
with those new metrics.
-- I have just updated the evaluation code so that you will be able to obtain new global metric errors. Those are:
-
RTE (root translation error): We compute the Euclidean distance of the global trajectory (i.e., world translation) of GT and prediction after the rigid alignment (rotation and translation). Unlike the previous values, we normalize this with the actual displacement of the subject so that this error is not dependent on the sequence length.
-
Jitter: We compute jitter (10 m / s^3) in the global coordinate. This implies how jittery the motion is in the global coordinate.
-
FS (foot sliding): We compute the averaged displacement of foot vertices during the contact. We obtain the contact label following the previous literature.
We will update the arXiv paper with new metrics accordingly.
from wham.
Hi,
Tried the new update, i don't see any improvement in the foot sliding nor in the jitter, was it implemented ?
Thank you!
from wham.
Related Issues (20)
- Clarification on Commercial Use of WHAM with MIT License HOT 1
- Regarding the DPVO format
- RuntimeError: CUDA error: out of memory HOT 2
- The meaning of updating intrinsics HOT 1
- Inquiry on the purpose on the normalization of SLAM camera 6D angular velocity HOT 1
- Getting rotation information from results (demo.py) HOT 2
- Error related to ffmpeg HOT 2
- The released training code is right? HOT 4
- Question about SMPL preprocessing
- WHAM version conflicts with DPVO HOT 3
- Question about new metrics
- bvh exporting
- Error when running in docker
- the keypoints founded are nan
- Processing detail of Human3.6m, MPI-INF-3DHP, and InstaVariety
- Question about vel_root.
- RICH bounding box determination
- How to Perform Real-time Motion Capture with WHAM
- Problem with Jump motion
- Process BEDLAM dataset?
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 wham.