Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images

2015-11-07 · CVPR 2016 6 · Shuran Song, Jianxiong Xiao

We focus on the task of amodal 3D object detection in RGB-D images, which aims to produce a 3D bounding box of an object in metric form at its full extent. We introduce Deep Sliding Shapes, a 3D ConvNet formulation that takes a 3D volumetric scene from a RGB-D image as input and outputs 3D object bounding boxes. In our approach, we propose the first 3D Region Proposal Network (RPN) to learn objectness from geometric shapes and the first joint Object Recognition Network (ORN) to extract geometric features in 3D and color features in 2D. In particular, we handle objects of various sizes by training an amodal RPN at two different scales and an ORN to regress 3D bounding boxes. Experiments show that our algorithm outperforms the state-of-the-art by 13.8 in mAP and is 200x faster than the original Sliding Shapes. All source code and pre-trained models will be available at GitHub.

📄 PDF Abstract BibTeX arXiv:1511.02300

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionObjectobject-detection Object Detection Object RecognitionRegion Proposal

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation

2020-12-02 · Won-Dong Jang, Donglai Wei, Xingxuan Zhang, Brian Leahy 외

Blastomere instance segmentation is important for analyzing embryos' abnormality. To measure the accurate shapes and sizes of blastomeres, their amodal segmentation is necessary. Amodal instance segmentation aims to reco…

Amodal Instance Segmentation Instance Segmentation Object Segmentation+1

3D-SSD: Learning Hierarchical Features from RGB-D Images for Amodal 3D Object Detection

2017-11-01 · Qianhui Luo, Huifang Ma, Yue Wang, Li Tang 외

This paper aims at developing a faster and a more accurate solution to the amodal 3D object detection problem for indoor scenes. It is achieved through a novel neural network that takes a pair of RGB-D images as the inpu…

3D Object Detection object-detection Object Detection

MUVA: A New Large-Scale Benchmark for Multi-View Amodal Instance Segmentation in the Shopping Scenario

2023-01-01 · ICCV 2023 1 · Zhixuan Li, Weining Ye, Juan Terven, Zachary Bennett 외

Amodal Instance Segmentation (AIS) endeavors to accurately deduce complete object shapes that are partially or fully occluded. However, the inherent ill-posed nature of single-view datasets poses challenges in determ…

Amodal Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation

Amodal Detection of 3D Objects: Inferring 3D Bounding Boxes From 2D Ones in RGB-Depth Images

2017-07-01 · CVPR 2017 7 · Zhuo Deng, Longin Jan Latecki

This paper addresses the problem of amodal perception of 3D object detection. The task is to not only find object localizations in the 3D world, but also estimate their physical sizes and poses, even if only parts of the…

3D Object Detection Object object-detection Object Detection

Variational Amodal Object Completion

2020-12-01 · NeurIPS 2020 12 · Huan Ling, David Acuna, Karsten Kreis, Seung Wook Kim 외

In images of complex scenes, objects are often occluding each other which makes perception tasks such as object detection and tracking, or robotic control tasks such as planning, challenging. To facilitate downstream tas…

Object object-detection Object Detection