Category Level Object Pose Estimation via Neural Analysis-by-Synthesis

08/18/2020
by   Xu Chen, et al.
0

Many object pose estimation algorithms rely on the analysis-by-synthesis framework which requires explicit representations of individual object instances. In this paper we combine a gradient-based fitting procedure with a parametric neural image synthesis module that is capable of implicitly representing the appearance, shape and pose of entire object categories, thus rendering the need for explicit CAD models per object instance unnecessary. The image synthesis network is designed to efficiently span the pose configuration space so that model capacity can be used to capture the shape and local appearance (i.e., texture) variations jointly. At inference time the synthesized images are compared to the target via an appearance based loss and the error signal is backpropagated through the network to the input parameters. Keeping the network parameters fixed, this allows for iterative optimization of the object pose, shape and appearance in a joint manner and we experimentally show that the method can recover orientation of objects with high accuracy from 2D images alone. When provided with depth measurements, to overcome scale ambiguities, the method can accurately recover the full 6DOF pose successfully.

READ FULL TEXT
research
02/01/2022

CLA-NeRF: Category-Level Articulated Neural Radiance Field

We propose CLA-NeRF – a Category-Level Articulated Neural Radiance Field...
research
07/27/2022

ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization

Our method studies the complex task of object-centric 3D understanding f...
research
12/19/2016

Parsing Images of Overlapping Organisms with Deep Singling-Out Networks

This work is motivated by the mostly unsolved task of parsing biological...
research
03/25/2022

A Visual Navigation Perspective for Category-Level Object Pose Estimation

This paper studies category-level object pose estimation based on a sing...
research
06/28/2018

Robust pose tracking with a joint model of appearance and shape

We present a novel approach for estimating the 2D pose of an articulated...
research
03/23/2023

TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimation

We propose a novel method for joint estimation of shape and pose of rigi...
research
08/01/2018

Category-level 6D Object Pose Recovery in Depth Images

Intra-class variations, distribution shifts among source and target doma...

Please sign up or login with your details

Forgot password? Click here to reset