Task
In the semantic segmentation of 4D point clouds, we want to infer the semantic label of each 3D point. Therefore, the input of all evaluated methods is a list of coordinates of 3D points. E-ach method should then output a label for each point of the scan.
Metric
We use mean Jaccard or so-called intersection-over-union (mIoU) over all classes, i.e.,
Leaderboard
Task
In this task, we need to give each frame of the point cloud in the point cloud video an action category label. The task’s input is a point cloud video and the output is the action described in each frame of this video.
Task
The following three metrics are reported: framewise accuracy (Acc), segmental edit distance, as well as segmental F1 scores at the overlapping thresholds of 10%, 25%, and 50%. Overlapping thresholds are determined by the IoU ratio.
Leaderboard
The following leaderboard contains only published approaches, where we at least can provide an arXiv link.
Approach | Paper | Code | Institution | Acc | Edit | Details |
---|---|---|---|---|---|---|
alisa_24 | ZJU | 0.8524140508221226 | 87.82051441704616 |
|
||
alisa_25 | ZJU | 0.852406576980568 | 87.81265092940069 |
|
||
XD-Transformer | SH ailab | 0.8522496263079222 | 91.38732622245608 |
|
||
XD-Transformer | ailab | 0.852219730941704 | 91.17519481582283 |
|
||
alisa_29 | ZJU | 0.851831091180867 | 87.97478083010287 |
|
||
HexFormer | PKU | 0.8518086696562033 | 88.94718917874394 |
|
||
alisa_14 | ZJU | 0.851136023916293 | 88.07147602447434 |
|
||
panda | ZJU | 0.851136023916293 | 88.07147602447434 |
|
||
alisa_27 | ZJU | 0.8511210762331839 | 88.07147602447434 |
|
||
alisa_26 | ZJU | 0.8509865470852018 | 88.23664347531256 |
|
||
alisa_7 | ZJU | 0.8509043348281017 | 87.93221777671194 |
|
||
alisa_9 | ZJU | 0.8509043348281017 | 87.93221777671194 |
|
||
alisa_29 | ZJU | 0.8508221225710015 | 88.26772105034811 |
|
||
alisa_28 | ZJU | 0.8504783258594918 | 88.22079506901783 |
|
||
alisa_30 | ZJU | 0.8492077727952168 | 87.75859590370912 |
|
||
alisa_31 | ZJU | 0.8491405082212257 | 88.19816637961415 |
|
||
alisa_21 | ZJU | 0.8480269058295964 | 88.20078933704173 |
|
||
alisa_19 | ZJU | 0.8469506726457399 | 87.36048862585304 |
|
||
alisa_22 | ZJU | 0.8468385650224215 | 86.99802585040757 |
|
||
alisa_23 | ZJU | 0.8467713004484305 | 87.15078206249964 |
|
||
alisa_16 | ZJU | 0.8465097159940209 | 88.22798408864078 |
|
||
alisa_17 | ZJU | 0.8462331838565023 | 86.93902979158919 |
|
||
alisa_20 | ZJU | 0.8461061285500747 | 87.62795308884864 |
|
||
alisa_18 | ZJU | 0.8460762331838565 | 86.88416127905313 |
|
||
alisa_15 | ZJU | 0.8460463378176383 | 85.61009813281167 |
|
||
alisa_11 | ZJU | 0.8444095665171898 | 86.712727305296 |
|
||
alisa_12 | ZJU | 0.8442899850523169 | 86.92284630931188 |
|
||
alisa_13 | ZJU | 0.8437817638266069 | 86.837199868755 |
|
||
Multi-Conv-Res7 | Dalian University of Technology | 0.8436920777279522 | 86.56866819963777 |
|
||
alisa_10 | ZJU | 0.8410762331838565 | 84.30390405384944 |
|
||
cos_version26 | ailab | 0.8406053811659193 | 91.05057053069882 |
|
||
cos_version29 | ailab | 0.8405979073243647 | 91.0819170320088 |
|
||
SAT_Merge_v1 | SH ailab | 0.8405979073243647 | 91.0779665729014 |
|
||
cos_version28 | ailab | 0.8405904334828102 | 91.07390934462893 |
|
||
cos_version19 | ailab | 0.8405829596412556 | 90.93773806749792 |
|
||
cos_version24 | ailab | 0.8405680119581465 | 90.96080366526259 |
|
||
Multi-Conv-Res5 | Dalian University of Technology | 0.8405530642750374 | 85.57560849851167 |
|
||
cos_version23 | ailab | 0.8405306427503737 | 90.91913658434308 |
|
||
cos_version23 | ailab | 0.8405306427503737 | 90.91913658434308 |
|
||
SAT_MERGE | SH ailab | 0.8404783258594918 | 91.05041810266165 |
|
||
SAT_Merge_v2 | SH ailab | 0.8404783258594918 | 91.05041810266165 |
|
||
SAT_Merge_v2 | SH ailab | 0.8404783258594918 | 91.05041810266165 |
|
||
Sat_Merge_v3 | SH ailab | 0.8404783258594918 | 91.05041810266165 |
|
||
Multi-Conv-Res6 | Dalian University of Technology | 0.8385201793721974 | 85.79122676098416 |
|
||
cos_version21 | ailab | 0.8376905829596413 | 91.11819971137608 |
|
||
alisa_8 | ZJU | 0.8372720478325859 | 80.6485018098239 |
|
||
Multi-Conv-Res8 | Dalian University of Technology | 0.8368385650224215 | 88.65632600109427 |
|
||
cos_version18 | ailab | 0.8350896860986547 | 91.07177872421552 |
|
||
cos_version21 | ailab | 0.8350896860986547 | 91.07177872421552 |
|
||
X4D-SceneFormer | No Disclosure | 0.8322496263079223 | 90.62816999024744 |
|
Task
In this task, the input is a point cloud video, and given the pose of the object in the first frame, we track this object and give the pose of the object in every frame thereafter. Note that we are referring to the category-level object poses.
Task
The following metrics are used: 5°5cm: percentage of estimates with orientation error <5°and translation error <5cm. Rerr: mean orientation error in degrees. Terr: mean translation error in centimeters.
Leaderboard
The following leaderboard contains only published approaches, where we at least can provide an arXiv link.
Approach | Paper | Code | Institution | Details |
---|