|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM364264365 |
| 003 |
DE-627 |
| 005 |
20240308232134.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3330866
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1320.xml
|
| 035 |
|
|
|a (DE-627)NLM364264365
|
| 035 |
|
|
|a (NLM)37934646
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Liu, Haisong
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Learning Optical Flow and Scene Flow With Bidirectional Camera-LiDAR Fusion
|
| 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 08.03.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an "early-fusion" or "late-fusion" manner. Such one-size-fits-all approaches suffer from a dilemma of failing to fully utilize the characteristic of each modality or to maximize the inter-modality complementarity. To address the problem, we propose a novel end-to-end framework, which consists of 2D and 3D branches with multiple bidirectional fusion connections between them in specific layers. Different from previous work, we apply a point-based 3D branch to extract the LiDAR features, as it preserves the geometric structure of point clouds. To fuse dense image features and sparse point features, we propose a learnable operator named bidirectional camera-LiDAR fusion module (Bi-CLFM). We instantiate two types of the bidirectional fusion pipeline, one based on the pyramidal coarse-to-fine architecture (dubbed CamLiPWC), and the other one based on the recurrent all-pairs field transforms (dubbed CamLiRAFT). On FlyingThings3D, both CamLiPWC and CamLiRAFT surpass all existing methods and achieve up to a 47.9% reduction in 3D end-point-error from the best published result. Our best-performing model, CamLiRAFT, achieves an error of 4.26% on the KITTI Scene Flow benchmark, ranking 1st among all submissions with much fewer parameters. Besides, our methods have strong generalization performance and the ability to handle non-rigid motion
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Lu, Tao
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Yihui
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Liu, Jia
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Wang, Limin
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 4 vom: 07. März, Seite 2378-2395
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:4
|g day:07
|g month:03
|g pages:2378-2395
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3330866
|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 4
|b 07
|c 03
|h 2378-2395
|