SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings

11/26/2021
by   Rasmus Laurvig Haugaard, et al.
0

We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the query- and key models learn to represent accurate multi-modal surface distributions. Our pose estimation method improves the state-of-the-art significantly on the comprehensive BOP Challenge, trained purely on synthetic data, even compared with methods trained on real data. The project site is at https://surfemb.github.io/ .

READ FULL TEXT

page 1

page 7

page 8

research
03/29/2022

OSOP: A Multi-Stage One Shot Object Pose Estimation Framework

We present a novel one-shot method for object detection and 6 DoF pose e...
research
10/03/2022

Multi-view object pose estimation from correspondence distributions and epipolar geometry

In many automation tasks involving manipulation of rigid objects, the po...
research
08/03/2022

SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation

This paper presents an efficient symmetry-agnostic and correspondence-fr...
research
03/17/2022

ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation

Establishing correspondences from image to 3D has been a key task of 6Do...
research
07/30/2022

Neural Correspondence Field for Object Pose Estimation

We propose a method for estimating the 6DoF pose of a rigid object with ...
research
11/12/2020

Fast robust peg-in-hole insertion with continuous visual servoing

This paper demonstrates a visual servoing method which is robust towards...
research
09/06/2018

Dense Pose Transfer

In this work we integrate ideas from surface-based modeling with neural ...

Please sign up or login with your details

Forgot password? Click here to reset