QaQ: Robust 6D Pose Estimation via Quality-Assessed RGB-D Fusion - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

QaQ: Robust 6D Pose Estimation via Quality-Assessed RGB-D Fusion

Abstract

RGB-D 6D pose estimation has recently drawn great research attention thanks to the complementary depth information. Whereas, the depth and the color image are often noisy in real industrial scenarios. Therefore, it becomes challenging for many existing methods that fuse equally RGB and depth features. In this paper, we present a novel fusion design to adaptively merge RGB-D cues. Specifically, we created a Qualityassessment block that estimates the global quality of the input modalities. This quality represented as an α parameter is then used to reinforce the fusion. We have thus found a simple and effective way to improve the robustness to low-quality inputs in terms of Depth and RGB. Extensive experiments on 6D pose estimation demonstrate the efficiency of our method, especially when noise is present in the input.
Fichier principal
Vignette du fichier
MVA_2023.pdf (2.36 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04166639 , version 1 (20-07-2023)

Identifiers

  • HAL Id : hal-04166639 , version 1

Cite

Théo Petitjean, Zongwei Wu, Olivier Laligant, Cédric Demonceaux. QaQ: Robust 6D Pose Estimation via Quality-Assessed RGB-D Fusion. 18th International Conference on Machine Vision Application, Jul 2023, Hamamatsu, Japan. ⟨hal-04166639⟩
35 View
67 Download

Share

Gmail Facebook X LinkedIn More