|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM370970209 |
| 003 |
DE-627 |
| 005 |
20250306015905.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240413s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2024.3388042
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1235.xml
|
| 035 |
|
|
|a (DE-627)NLM370970209
|
| 035 |
|
|
|a (NLM)38607712
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Wei, Wen-Li
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Bridging Actions
|b Generate 3D Poses and Shapes In-Between Photos
|
| 264 |
|
1 |
|c 2024
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 03.10.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Generating realistic 3D human motion has been a fundamental goal of the game/animation industry. This work presents a novel transition generation technique that can bridge the actions of people in the foreground by generating 3D poses and shapes in-between photos, allowing 3D animators/novice users to easily create/edit 3D motions. To achieve this, we propose an adaptive motion network (ADAM-Net) that effectively learns human motion from masked action sequences to generate kinematically compliant 3D poses and shapes in-between given temporally-sparse photos. Three core learning designs underpin ADAM-Net. First, we introduce a random masking process that randomly masks images from an action sequence and fills masked regions in latent space by interpolation of unmasked images to simulate various transitions under given temporally-sparse photos. Second, we propose a long-range adaptive motion (L-ADAM) attention module that leverages visual cues observed from human motion to adaptively recalibrate the range that needs attention in a sequence, along with a multi-head cross-attention. Third, we develop a short-range adaptive motion (S-ADAM) attention module that weightedly selects and integrates adjacent feature representations at different levels to strengthen temporal correlation. By coupling these designs, the results demonstrate that ADAM-Net excels not only in generating 3D poses and shapes in-between photos, but also in classic 3D human pose and shape estimation
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lin, Jen-Chun
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 11 vom: 12. Nov., Seite 7232-7250
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnas
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:11
|g day:12
|g month:11
|g pages:7232-7250
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2024.3388042
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 46
|j 2024
|e 11
|b 12
|c 11
|h 7232-7250
|