Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction

被引:1
|
作者
Liu, YuXuan [1 ,2 ]
Mishra, Nikhil [1 ,2 ]
Sieb, Maximilian [1 ]
Shentu, Yide [1 ,2 ]
Abbeel, Pieter [1 ,2 ]
Chen, Xi [1 ]
机构
[1] Covariant, Emeryville, CA 94608 USA
[2] Univ Calif Berkeley, Berkeley, CA 94720 USA
来源
关键词
3D bounding boxes; 3D bounding box estimation; 3D object detection; Autoregressive models; Uncertainty modeling;
D O I
10.1007/978-3-031-20080-9_39
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
3D bounding boxes are a widespread intermediate representation in many computer vision applications. However, predicting them is a challenging task, largely due to partial observability, which motivates the need for a strong sense of uncertainty. While many recent methods have explored better architectures for consuming sparse and unstructured point cloud data, we hypothesize that there is room for improvement in the modeling of the output distribution and explore how this can be achieved using an autoregressive prediction head. Additionally, we release a simulated dataset, COB-3D, which highlights new types of ambiguity that arise in real-world robotics applications, where 3D bounding box prediction has largely been underexplored. We propose methods for leveraging our autoregressive model to make high confidence predictions and meaningful uncertainty measures, achieving strong results on SUN-RGBD, Scannet, KITTI, and our new dataset.
引用
收藏
页码:673 / 694
页数:22
相关论文
共 50 条
  • [1] Poster: AutoSense: Reliable 3D Bounding Box Prediction for Vehicles
    Regmi, Hem
    Tavasoli, Reza
    Telaak, Joseph
    Sur, Sanjib
    Nelakuditi, Srihari
    [J]. PROCEEDINGS OF THE 2024 THE 22ND ANNUAL INTERNATIONAL CONFERENCE ON MOBILE SYSTEMS, APPLICATIONS AND SERVICES, MOBISYS 2024, 2024, : 674 - 675
  • [2] PrimitivePose: Generic Model and Representation for 3D Bounding Box Prediction of Unseen Objects
    Kriegler, Andreas
    Beleznai, Csaba
    Gelautz, Margrit
    Murschitz, Markus
    Goebel, Kai
    [J]. INTERNATIONAL JOURNAL OF SEMANTIC COMPUTING, 2023, 17 (03) : 387 - 410
  • [3] 3D object Classification using Bounding box
    Malwe, Gauri
    Kshirsagar, Deepak
    Madkaikar, Ashish
    [J]. 2018 FOURTH INTERNATIONAL CONFERENCE ON COMPUTING COMMUNICATION CONTROL AND AUTOMATION (ICCUBEA), 2018,
  • [4] Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver
    Liu, Xianpeng
    Zheng, Ce
    Cheng, Kelvin
    Xue, Nan
    Qi, Guo-Jun
    Wu, Tianfu
    [J]. 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 6413 - 6423
  • [5] PrimitivePose: 3D Bounding Box Prediction of Unseen Objects via Synthetic Geometric Primitives
    Kriegler, Andreas
    Beleznai, Csaba
    Murschitz, Markus
    Goebel, Kai
    Gelautz, Margrit
    [J]. 2022 SIXTH IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING, IRC, 2022, : 190 - 197
  • [6] Efficient Similarity Search on 3D Bounding Box Annotations
    Kriegel, Hans-Peter
    Petri, Marisa
    Schubert, Matthias
    Shekelyan, Michael
    Stockerl, Michael
    [J]. MEDICAL IMAGING 2012: ADVANCED PACS-BASED IMAGING INFORMATICS AND THERAPEUTIC APPLICATIONS, 2012, 8319
  • [7] PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation
    Xu, Danfei
    Anguelov, Dragomir
    Jain, Ashesh
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 244 - 253
  • [8] 3D Bounding Box Estimation Using Deep Learning and Geometry
    Mousavian, Arsalan
    Anguelov, Dragomir
    Flynn, John
    Kosecka, Jana
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5632 - 5640
  • [9] Vehicle Detection Using Point Cloud and 3D LIDAR Sensor to Draw 3D Bounding Box
    Gagana, H. S.
    Sunitha, N. R.
    Nishanth, K. N.
    [J]. COMPUTATIONAL VISION AND BIO-INSPIRED COMPUTING, 2020, 1108 : 983 - 992
  • [10] Multi-View Classification and 3D Bounding Box Regression Networks
    Pramerdorfer, Christopher
    Kampel, Martin
    Van Loock, Mark
    [J]. 2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2018, : 734 - 739