Comments (6)
您可以看一些评测部分。
我们采用了两套评测protocol。一套是3DPW challenge的,另一套是之前方法(VIBE,SPIN,HMR等)评测采用的范式。
ROMP作为一个one-stage bottom-up方法一直是整张图输入的,没有crop过。可以看一下/跑一下我们的评测代码确认。
我们这里求bbox只是用于将输出结果和ground truth匹配,不然没法评测。
我们的目前的方法没有加tracking功能,所以只能评测with association那个track。不评测tracking性能。
至于其他方法,他们有自己的pipeline,有的可能是top-down的,您应该有判断,这里就不评价了。
from romp.
感谢!
from romp.
@Arthur151 抱歉,再打扰一下! 请问可以提供一下您这边划分的3DPW-OC, 3DPW-PC, 3DPW-NC子数据集或者划分方式/代码吗
from romp.
PW3D_PCsubset = {'courtyard_basketball_00':[200,280], 'courtyard_captureSelfies_00':[500,600],
'courtyard_dancing_00':[60,370], 'courtyard_dancing_01':[60,270], 'courtyard_hug_00':[100,500], 'downtown_bus_00':[1620,1900]}
PW3D_OCsubset = ['courtyard_backpack','courtyard_basketball','courtyard_bodyScannerMotions','courtyard_box','courtyard_golf','courtyard_jacket',
'courtyard_laceShoe','downtown_stairs','flat_guitar','flat_packBags','outdoors_climbing','outdoors_crosscountry','outdoors_fencing','outdoors_freestyle',
'outdoors_golf','outdoors_parcours','outdoors_slalom']
NC是其余的
from romp.
您可以看一些评测部分。 我们采用了两套评测protocol。一套是3DPW challenge的,另一套是之前方法(VIBE,SPIN,HMR等)评测采用的范式。 ROMP作为一个one-stage bottom-up方法一直是整张图输入的,没有crop过。可以看一下/跑一下我们的评测代码确认。 我们这里求bbox只是用于将输出结果和ground truth匹配,不然没法评测。 我们的目前的方法没有加tracking功能,所以只能评测with association那个track。不评测tracking性能。 至于其他方法,他们有自己的pipeline,有的可能是top-down的,您应该有判断,这里就不评价了。
你好,如果在一张图中,ROMP没有检测出人或者检测多了一个人,找不到和ground truth匹配的时候,要怎么计算评测指标呢?
from romp.
你可以参见这里,我们给miss的填充了0姿态的三维人体网格。
3DPW不评测检测性能,因为确实图中有些人是没有3D标注的。多出来的估计不会被评测。
from romp.
Related Issues (20)
- KeyError: 'pw3d_vibe-MPJPE'
- AttributeError: 'TRACE' object has no attribute 'smpl_model_path' HOT 1
- 相機外參問題
- KeyError: 'joints_smpl24' HOT 3
- romp smpl output poses is not fit with f_smpl/m_smpl.fbx HOT 1
- Permission denied: '/home/yusun' when running demo of TRACE HOT 2
- EVAL CMU dataset HOT 1
- Export Trace results to motion files like AMASS
- TRACE's result on MuPoTS-3D dataset
- Extending Pose Estimation Model for 3D Objects: Customization and Challenges
- No file or directory
- missing files
- pth generation HOT 1
- 大佬您好,想请问下世界坐标系下的可视化问题。 HOT 1
- RuntimeError: Sizes of tensors must match except in dimension 1
- convert2fbx.py multiple person
- Creating avatar on the live cam window
- Fail to track more than one person in each frame HOT 1
- How to get the principal point?
- aitviewer, visualize error
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 romp.