paper-with-me

홈 › Papers

Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

2023-04-03 · ICCV 2023 1 · Xianpeng Liu, Ce Zheng, Kelvin Cheng, Nan Xue, Guo-Jun Qi, Tianfu Wu

The main challenge of monocular 3D object detection is the accurate localization of 3D center. Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner. Specifically, we first obtain initial proposals from off-the-shelf backbone monocular 3D detectors. Then, we generate a 3D anchor space by local-grid sampling from the initial proposals. Finally, we perform 3D bounding box denoising at the 3D-to-2D proposal verification stage. To effectively learn discriminative features for denoising highly overlapped proposals, this paper presents a method of using the Perceiver I/O model to fuse the 3D-to-2D geometric information and the 2D appearance information. With the encoded latent representation of a proposal, the verification head is implemented with a self-attention module. Our method, named as MonoXiver, is generic and can be easily adapted to any backbone monocular 3D detectors. Experimental results on the well-established KITTI dataset and the challenging large-scale Waymo dataset show that MonoXiver consistently achieves improvement with limited computation overhead.

📄 PDF Abstract BibTeX arXiv:2304.01289

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionDenoisingMonocular 3D Object Detectionobject-detectionObject Detection

Similar Papers 제목 키워드 기반

VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Rendering

2025-12-01 · Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi arxiv

Monocular 3D object detection is a fundamental yet challenging task in 3D scene understanding. Existing approaches heavily depend on supervised learning with extensive 3D annotations, which are often acquired from LiDAR …

Monocular 3D Object DetectionScene UnderstandingPoint Clouds

Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels

2020-10-07 · L. Koestler, N. Yang, R. Wang, D. Cremers

The training of deep-learning-based 3D object detectors requires large datasets with 3D bounding box labels for supervision that have to be generated by hand-labeling. We propose a network architecture and training proce…

3D Object DetectionMonocular 3D Object DetectionObjectobject-detection+2

Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection

2021-12-09 · Xianpeng Liu, Nan Xue, Tianfu Wu

Monocular 3D object detection aims to localize 3D bounding boxes in an input single 2D image. It is a highly challenging problem and remains open, especially when no extra information (e.g., depth, lidar and/or multi-fra…

3D Object DetectionMonocular 3D Object DetectionObjectobject-detection+2

Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

2020-02-05 · Yingjie Cai, Buyu Li, Zeyu Jiao, Hongsheng Li 외

Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, th…

3D Object DetectionDepth EstimationMonocular 3D Object DetectionObject+2

Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud

2019-03-23 · Xinshuo Weng, Kris Kitani

Monocular 3D scene understanding tasks, such as object size estimation, heading angle estimation and 3D localization, is challenging. Successful modern day methods for 3D scene understanding require the use of a 3D senso…

3D Object DetectionDepth EstimationMonocular 3D Object DetectionMonocular Depth Estimation+4