Extra FAT: A Photorealistic Dataset for 6D Object Pose Estimation

2020 ◽  
Vol 2020 (8) ◽  
pp. 221-1-221-7
Author(s):  
Jianhang Chen ◽  
Daniel Mas Montserrat ◽  
Qian Lin ◽  
Edward J. Delp ◽  
Jan P. Allebach
Keyword(s):  
Object Detection ◽  
Pose Estimation ◽  
Object Segmentation ◽  
3D Object ◽  
Virtual Camera ◽  
Image Dataset ◽  
Rgb Images ◽  
Object Pose Estimation ◽  
Object Models

We introduce a new image dataset for object detection and 6D pose estimation, named Extra FAT. The dataset consists of 825K photorealistic RGB images with annotations of groundtruth location and rotation for both the virtual camera and the objects. A registered pixel-level object segmentation mask is also provided for object detection and segmentation tasks. The dataset includes 110 different 3D object models. The object models were rendered in five scenes with diverse illumination, reflection, and occlusion conditions.

Learning Robust Features for 3D Object Pose Estimation

2021 ◽  
Author(s):  
Christos Papaioannidis ◽  
Ioannis Pitas
Keyword(s):  
Pose Estimation ◽  
3D Object ◽  
Object Pose Estimation

Pose Guided RGBD Feature Learning for 3D Object Pose Estimation

2017 ◽  
Author(s):  
Vassileios Balntas ◽  
Andreas Doumanoglou ◽  
Caner Sahin ◽  
Juil Sock ◽  
Rigas Kouskouridas ◽  
...  
Keyword(s):  
Pose Estimation ◽  
Feature Learning ◽  
3D Object ◽  
Object Pose Estimation

scholarly journals A Novel Regional Fusion Network for 3D Object Detection based on RGB Images and Point Clouds

2021 ◽  
Author(s):  
Hung-Hao Chen ◽  
Chia-Hung Wang ◽  
Hsueh-Wei Chen ◽  
Pei-Yung Hsiao ◽  
Li-Chen Fu ◽  
...  
Keyword(s):  
Object Detection ◽  
Receptive Fields ◽  
Point Clouds ◽  
Detection Methods ◽  
Lidar Data ◽  
3D Object ◽  
Multi Scale ◽  
Interest Level ◽  
Rgb Images ◽  
3D Object Detection

The current fusion-based methods transform LiDAR data into bird’s eye view (BEV) representations or 3D voxel, leading to information loss and heavy computation cost of 3D convolution. In contrast, we directly consume raw point clouds and perform fusion between two modalities. We employ the concept of region proposal network to generate proposals from two streams, respectively. In order to make two sensors compensate the weakness of each other, we utilize the calibration parameters to project proposals from one stream onto the other. With the proposed multi-scale feature aggregation module, we are able to combine the extracted regionof-interest-level (RoI-level) features of RGB stream from different receptive fields, resulting in fertilizing feature richness. Experiments on KITTI dataset show that our proposed network outperforms other fusion-based methods with meaningful improvements as compared to 3D object detection methods under challenging setting.

Sign in / Sign up

Export Citation Format

Share Document