已入深夜,您辛苦了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!祝你早点完成任务,早点休息,好梦!

FARP-Net: Local-Global Feature Aggregation and Relation-Aware Proposals for 3D Object Detection

计算机科学 特征(语言学) 人工智能 数据挖掘 关系(数据库) 目标检测 计算机视觉 对象(语法) 模式识别(心理学) 哲学 语言学
作者
Tao Xie,Li Wang,Ke Wang,Ruifeng Li,Xinyu Zhang,Haoming Zhang,Linqi Yang,Huaping Liu,Jun Li
出处
期刊:IEEE Transactions on Multimedia [Institute of Electrical and Electronics Engineers]
卷期号:26: 1027-1040 被引量:17
标识
DOI:10.1109/tmm.2023.3275366
摘要

In this work, we introduce FARP-Net, an adaptive local-global feature aggregation and relation-aware proposal network for high-quality 3D object detection from pure point clouds. Our key insight is that learning adaptive local-global feature aggregation from an irregular yet sparse point cloud and generating superb proposals are both pivotal for detection. Technically, we propose a novel local-global feature aggregation layer (LGFAL) that fully exploits the complementary correlation between local features and global features, and fuses their strengths adaptively via an attention-based fusion module. Furthermore, we incorporate a lightweight feature affine module (LFAM) into LGFAL to map the local features into a normal distribution, thus acquiring fine-grained features of each local region in a weight-sharing manner. During object proposal generation, we propose a weighted relation-aware proposal module (WRPM) that uses an objectness-aware formalism to weigh the relation importance among object candidates for a clear and principal context, thereby facilitating the generation of high-quality proposals. The WRPM challenges the traditional practice of extracting contextual information among all object candidates, which is inefficient as object candidates are always noisy and redundant. Experimentally, FARP-Net delivers superior performance on two widely used benchmarks with fewer parameters, 64.0% mAP@0.25 on the SUN RGB-D dataset and 70.9% mAP@0.25 on the ScanNet V2 dataset. We further validate that the proposed LGFAL and WRPM can be integrated into both indoor and outdoor detectors to boost performance.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
Hu完成签到,获得积分10
4秒前
yliaoyou完成签到,获得积分10
4秒前
zzzzzz完成签到 ,获得积分10
7秒前
7秒前
8秒前
10秒前
Mars_1108发布了新的文献求助10
13秒前
14秒前
天天快乐应助称心元枫采纳,获得10
17秒前
小智发布了新的文献求助10
17秒前
17秒前
小小杜发布了新的文献求助10
17秒前
19秒前
小二郎应助xxw采纳,获得10
21秒前
22秒前
23秒前
kaka完成签到,获得积分10
23秒前
cjyyy完成签到,获得积分20
23秒前
连难胜完成签到 ,获得积分10
24秒前
俞秋烟完成签到,获得积分10
24秒前
小方发布了新的文献求助10
25秒前
27秒前
lllwy完成签到 ,获得积分10
27秒前
Orange应助周哲采纳,获得10
28秒前
Gumiano发布了新的文献求助10
29秒前
29秒前
小超人发布了新的文献求助10
29秒前
yahonyoyoyo发布了新的文献求助10
30秒前
HSA发布了新的文献求助10
30秒前
30秒前
JamesPei应助小智采纳,获得10
31秒前
Went完成签到,获得积分10
32秒前
科研通AI5应助yahonyoyoyo采纳,获得10
33秒前
33秒前
34秒前
温友儿完成签到,获得积分10
35秒前
37秒前
xiaofeiyan发布了新的文献求助30
40秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3976455
求助须知:如何正确求助?哪些是违规求助? 3520548
关于积分的说明 11203850
捐赠科研通 3257210
什么是DOI,文献DOI怎么找? 1798648
邀请新用户注册赠送积分活动 877835
科研通“疑难数据库(出版商)”最低求助积分说明 806539