Submission: Pix2Pose-BOP20-ICCV19/HB

Submission name
Submission time (UTC) Aug. 18, 2020, 7:38 a.m.
User kirumang
Task Pose estimation (BOP 2019-2022)
Dataset HB
Training model type Default
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AR:0.446
AR_MSPD:0.594
AR_MSSD:0.394
AR_VSD:0.352
average_time_per_image:0.982

Method: Pix2Pose-BOP20-ICCV19

User kirumang
Publication Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation, ICCV 2019
Implementation https://github.com/kirumang/Pix2Pose
Training image modalities RGB
Test image modalities RGB
Description

Poses are estimated using RGB images only without refinement. Results are derived after the following modifications from the original implementation of the paper. Other setups are the same as performed in BOP 2019.

1) Replaced the encoder part with the first three blocks of Resnet-50 with pre-trained weights using ImageNet.

2) Increased a threshold for inlier pixels during PnP-Ransac operation (3->5).

3) A minor bug that causes bad detection results for the T-Less dataset is fixed (different image resolutions were used during training and inference)

4) Increased the number of RPN proposals and NMS thresholds in Mask-RCNN (1000/0.7 to 2000/0.9), which produces more detection proposals

All updates will be shared in our public repository (checkout bop2020 branch after the deadline)

Computer specifications CPU: i7-9700K, GPU: Titan V, RAM: 32GB