VoteNet: A Deep Learning Label Fusion Method for Multi-atlas Segmentation

Ding, Zhipeng; Han, Xu; Niethammer, Marc

doi:10.1007/978-3-030-32248-9_23

Cited by 90 publications

(55 citation statements)

References 21 publications

(29 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The keypoints are also used to predict the center of the objects before we generate the RoIs. In fact, considering that these keypoints lie on the objects, inspired by [45], the spatial location and features of the keypoints can be used to estimate the centers of the corresponding objects.…”

Section: B Rois Fusion Layermentioning

confidence: 99%

RoIFusion: 3D Object Detection From LiDAR and Vision

2021

View full text Add to dashboard Cite

When localizing and detecting 3D objects for autonomous driving scenes, obtaining information from multiple sensors (e.g., camera, LIDAR) is capable of mutually offering useful complementary information to enhance the robustness of 3D detectors. In this paper, a deep neural network architecture, named RoIFusion, is proposed to efficiently fuse the multi-modality features for 3D object detection by leveraging the advantages of LIDAR and camera sensors. In order to achieve this task, instead of densely combining the point-wise feature of the point cloud with the related pixel features, our fusion method novelly aggregates a small set of 3D Region of Interests (RoIs) in the point clouds with the corresponding 2D RoIs in the images, which are beneficial for reducing the computation cost and avoiding the viewpoint misalignment during the feature aggregation from different sensors. Finally, Extensive experiments are performed on the KITTI 3D object detection challenging benchmark to show the effectiveness of our fusion method and demonstrate that our deep fusion approach achieves state-of-the-art performance.

show abstract

Section: B Rois Fusion Layermentioning

confidence: 99%

RoIFusion: 3D Object Detection From LiDAR and Vision

2021

View full text Add to dashboard Cite

show abstract

“…However, some indoor objects are not convex, so the geometrical center of an indoor object may not belong to this object (e.g., the center of a table or a chair might be in between legs). Accordingly, an object proposal given by a single center point might be irrelevant, so indoor methods use deep Hough voting to generate proposals [11,31,40].…”

Section: D Object Detectionmentioning

confidence: 99%

“…Therefore, instead of time-consuming custom architecture implementation, one can simply employ state-of-the-art methods with no modifications. However, the design of heads significantly differs for outdoor [22,39] and indoor [11,31] methods.…”

Section: Detection Headsmentioning

confidence: 99%

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

Rukhovich¹,

Воронцова²,

Konushin³

2021

Preprint

View full text Add to dashboard Cite

In this paper, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. To address this problem, we propose ImVoxelNet, a novel fully convolutional method of 3D object detection based on monocular or multi-view RGB images. The number of monocular images in each multi-view input can variate during training and inference; actually, this number might be unique for each multi-view input. ImVoxelNet successfully handles both indoor and outdoor scenes, which makes it general-purpose. Specifically, it achieves state-of-the-art results in car detection on KITTI (monocular) and nuScenes (multi-view) benchmarks among all methods that accept RGB images. Moreover, it surpasses existing RGB-based 3D object detection methods on the SUN RGB-D dataset. On ScanNet, ImVoxelNet sets a new benchmark for multiview 3D object detection. The source code and the trained models are available at https://github.com/saic-vul/imvoxelnet.Preprint. Under review.

show abstract

“…3D object detection [1,2,3] is an important task in computer vision and has various applications such as autonomous driving [4] and robotics [5,6]. The goal of this task is to estimate the categories and corresponding 3D bounding boxes of all targets in the scene.…”

Section: Introductionmentioning

confidence: 99%

Semi-Supervised 3d Object Detection Via Adaptive Pseudo-Labeling

Liu

Zhou

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

3D object detection is an important task in computer vision. Most existing methods require a large number of high-quality 3D annotations, which are expensive to collect. Especially for outdoor scenes, the problem becomes more severe due to the sparseness of the point cloud and the complexity of urban scenes. Semi-supervised learning is a promising technique to mitigate the data annotation issue. Inspired by this, we propose a novel semi-supervised framework based on pseudo-labeling for outdoor 3D object detection tasks. We design the Adaptive Class Confidence Selection module (ACCS) to generate high-quality pseudo-labels. Besides, we propose Holistic Point Cloud Augmentation (HPCA) for unlabeled data to improve robustness. Experiments on the KITTI benchmark demonstrate the effectiveness of our method. Code and supplementary material are available at https://github.com/tayson0825/SS3DOD.

show abstract

VoteNet: A Deep Learning Label Fusion Method for Multi-atlas Segmentation

Cited by 90 publications

References 21 publications

RoIFusion: 3D Object Detection From LiDAR and Vision

RoIFusion: 3D Object Detection From LiDAR and Vision

ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection

Semi-Supervised 3d Object Detection Via Adaptive Pseudo-Labeling

Contact Info

Product

Resources

About