Uni6Dv2: Noise Elimination for 6D Pose Estimation

TL;DR

Uni6Dv2 enhances 6D pose estimation by introducing a two-step denoising process that effectively reduces background and depth noise, leading to more accurate and robust pose predictions with less reliance on annotated data.

Contribution

The paper presents a novel two-step denoising approach for Uni6D that improves noise robustness and reduces annotation dependency in 6D pose estimation.

Findings

Outperforms Uni6D in accuracy and robustness.

Effectively reduces background and depth noise.

Maintains high inference efficiency.

Abstract

Uni6D is the first 6D pose estimation approach to employ a unified backbone network to extract features from both RGB and depth images. We discover that the principal reasons of Uni6D performance limitations are Instance-Outside and Instance-Inside noise. Uni6D's simple pipeline design inherently introduces Instance-Outside noise from background pixels in the receptive field, while ignoring Instance-Inside noise in the input depth data. In this paper, we propose a two-step denoising approach for dealing with the aforementioned noise in Uni6D. To reduce noise from non-instance regions, an instance segmentation network is utilized in the first step to crop and mask the instance. A lightweight depth denoising module is proposed in the second step to calibrate the depth feature before feeding it into the pose regression network. Extensive experiments show that our Uni6Dv2 reliably and robustly eliminates noise, outperforming Uni6D without sacrificing too much inference efficiency. It also reduces the need for annotated real data that requires costly labeling.