Submission: RADet+PFA-PBR-RGBD/ITODD

Download submission
Submission name
Submission time (UTC) Oct. 11, 2022, 6:54 a.m.
User Yang-hai
Task Model-based 6D localization of seen objects
Dataset ITODD
Training model type Default
Training image type Synthetic (only PBR images provided for BOP Challenge 2020 were used)
Description
Evaluation scores
AR:0.469
AR_MSPD:0.498
AR_MSSD:0.495
AR_VSD:0.413
average_time_per_image:1.396

Method: RADet+PFA-PBR-RGBD

User Yang-hai
Publication Yang Hai et, al; Rigidity-Aware Detection for 6D Object Pose Estimation; Yinlin Hu et, at: Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation, ECCV, 2022
Implementation
Training image modalities RGB
Test image modalities RGB-D
Description

We train a single model for all objects on each dataset, and based on an architecture of object detection and pose regression.

Object detection: extended FCOS

Pose regression: extended PFA-Pose

Data: PBR

RGBD track: the same models used in RGB Track, RANSAC-Kabsch for depth utilizing.

The Main differences from FCOS:

  1. We use stronger augmentations following the best practice in 6D pose estimation

  2. We utilize some mask information for a better sampling of positive signals during training

The main differences from the original PFA-Pose paper:

  • It does not use a detection component, we embed a detection component into it to facilitate the pose regression.

  • It uses exemplars rendered offline for training, which is resource-friendly and efficient during training. For this competition, we replace it with online rendering to achieve better accuracy.

  • It uses only flow from the rendered image to the input. We further use a backward flow from the input to the rendered image for a consistent check to remove more outliers.

List of contributors:

Yang Hai, Rui Song, Zhiqiang Liu, Jiaojiao Li (Xidian University)

Mathieu Salzmann, Pascal Fua (EPFL)

Yinlin Hu (Magic Leap)

Computer specifications NVIDIA 3090