Uni6Dv2: Noise Elimination for 6D Pose Estimation

  title={Uni6Dv2: Noise Elimination for 6D Pose Estimation},
  author={Mingshan Sun and Ye Zheng and Tianpeng Bao and Jianqiu Chen and Guoqiang Jin and Liwei Wu and Rui Zhao and Xiaoke Jiang},
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… 

Figures and Tables from this paper

Res6D: Projective Residual Regression for 6D Pose Estimation

This work generalizes the pin-hole camera projection model to a residual-based projection model and proposes the projective residual regression (Res6D) mechanism, which reduces the distribution gap and shrinks the regression target to a small range by regressing the residual between the target and the reference point.

Uni6Dv3: 5D Anchor Mechanism for 6D Pose Estimation

A 5D anchor mechanism by defining the anchor with 3D co- dinates in the physical space and 2D coordinates in the image plane is proposed, which achieves state-of-the-art overall results on datasets including Occlusion LineMOD, and requires only 10% of training data to reach comparable performance as full data.

Geo6D: Geometric Constraints Learning for 6D Pose Estimation

A geometric constraint-based 6D pose estimation method (Geo6D), which establishes an explicit geometric constraint between the input and the regression target, which achieves state-of-the-art performance on multiple datasets and shows significant effectiveness with limited data volume.



Mask R-CNN

This work presents a conceptually simple, flexible, and general framework for object instance segmentation that outperforms all existing, single-model entries on every task, including the COCO 2016 challenge winners.

Learning 6D Object Pose Estimation Using 3D Object Coordinates

This work addresses the problem of estimating the 6D Pose of specific objects from a single RGB-D image by presenting a learned, intermediate representation in form of a dense 3D object coordinate labelling paired with a dense class labelling.

Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation

As RGB-D sensors become more affordable, using RGB- D images to obtain high-accuracy 6D pose estimation results becomes a better option. State-of-the-art approaches typically use different backbones

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

This work proposes FFB6D, a Full Flow Bidirectional fusion network designed for 6D pose estimation from a single RGBD image, which learns to combine appearance and geometry information for representation learning as well as output representation selection.

PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation

A deep Hough voting network is proposed to detect 3D keypoints of objects and then estimate the 6D pose parameters within a least-squares fitting manner, which is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation.

DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion

DenseFusion is a generic framework for estimating 6D pose of a set of known objects from RGB-D images that processes the two data sources individually and uses a novel dense fusion network to extract pixel-wise dense feature embedding, from which the pose is estimated.

PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes

This work introduces PoseCNN, a new Convolutional Neural Network for 6D object pose estimation, which is highly robust to occlusions, can handle symmetric objects, and provide accurate pose estimation using only color images as input.

ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework

A computation efficient regression framework is presented for estimating the 6D pose of rigid objects from a single RGB-D image, which is applicable to handling symmetric objects and designs a symmetry-invariant pose distance metric, called average (maximum) grouped primitives distance or A(M)GPD.

Calibrated RGB-D Salient Object Detection

  • Wei JiJingjing Li Li Cheng
  • Computer Science
    2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
A Depth Calibration and Fusion (DCF) framework that contains two novel components: a learning strategy to calibrate the latent bias in the original depth maps towards boosting the SOD performance and a simple yet effective cross reference module to fuse features from both RGB and depth modalities.

GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation

A simple yet effective Geometry-guided Direct Regression Network (GDR-Net) to learn the 6D pose in an end-to-end manner from dense correspondence-based intermediate geometric representations, which remarkably outperforms state-of-the-art methods on LM, LM-O and YCB-V datasets.