|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM366246399 |
| 003 |
DE-627 |
| 005 |
20240404234516.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231227s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2023.3345880
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1364.xml
|
| 035 |
|
|
|a (DE-627)NLM366246399
|
| 035 |
|
|
|a (NLM)38133980
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Li, Jianan
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a MsSVT++
|b Mixed-Scale Sparse Voxel Transformer With Center Voting for 3D Object Detection
|
| 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 03.04.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Accurate 3D object detection in large-scale outdoor scenes, characterized by considerable variations in object scales, necessitates features rich in both long-range and fine-grained information. While recent detectors have utilized window-based transformers to model long-range dependencies, they tend to overlook fine-grained details. To bridge this gap, we propose MsSVT++, an innovative Mixed-scale Sparse Voxel Transformer that simultaneously captures both types of information through a divide-and-conquer approach. This approach involves explicitly dividing attention heads into multiple groups, each responsible for attending to information within a specific range. The outputs of these groups are subsequently merged to obtain final mixed-scale features. To mitigate the computational complexity associated with applying a window-based transformer in 3D voxel space, we introduce a novel Chessboard Sampling strategy and implement voxel sampling and gathering operations sparsely using a hash map. Moreover, an important challenge stems from the observation that non-empty voxels are primarily located on the surface of objects, which impedes the accurate estimation of bounding boxes. To overcome this challenge, we introduce a Center Voting module that integrates newly voted voxels enriched with mixed-scale contextual information towards the centers of the objects, thereby improving precise object localization. Extensive experiments demonstrate that our single-stage detector, built upon the foundation of MsSVT++, consistently delivers exceptional performance across diverse datasets
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Dong, Shaocong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ding, Lihe
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Tingfa
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 46(2024), 5 vom: 03. Apr., Seite 3736-3752
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:46
|g year:2024
|g number:5
|g day:03
|g month:04
|g pages:3736-3752
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2023.3345880
|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 5
|b 03
|c 04
|h 3736-3752
|