|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM359905854 |
| 003 |
DE-627 |
| 005 |
20231226081855.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3298645
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1199.xml
|
| 035 |
|
|
|a (DE-627)NLM359905854
|
| 035 |
|
|
|a (NLM)37490383
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Xu, Haofei
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Unifying Flow, Stereo and Depth Estimation
|
| 264 |
|
1 |
|c 2023
|
| 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 04.10.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images. Unlike previous specialized architectures for each specific task, we formulate all three tasks as a unified dense correspondence matching problem, which can be solved with a single model by directly comparing feature similarities. Such a formulation calls for discriminative feature representations, which we achieve using a Transformer, in particular the cross-attention mechanism. We demonstrate that cross-attention enables integration of knowledge from another image via cross-view interactions, which greatly improves the quality of the extracted features. Our unified model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks. We outperform RAFT with our unified model on the challenging Sintel dataset, and our final model that uses a few additional task-specific refinement steps outperforms or compares favorably to recent state-of-the-art methods on 10 popular flow, stereo and depth datasets, while being simpler and more efficient in terms of model design and inference speed
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Zhang, Jing
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Cai, Jianfei
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Rezatofighi, Hamid
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Yu, Fisher
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Tao, Dacheng
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Geiger, Andreas
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 11 vom: 25. Nov., Seite 13941-13958
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:11
|g day:25
|g month:11
|g pages:13941-13958
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3298645
|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 45
|j 2023
|e 11
|b 25
|c 11
|h 13941-13958
|