Category-Level Metric Scale Object Shape and Pose Estimation

TL;DR

This paper introduces a novel framework that jointly estimates object shape, size, and pose from a single RGB image, addressing the limitations of existing methods that lack metric scale and accurate positioning.

Contribution

It proposes a dual-branch approach combining metric scale shape estimation and normalized coordinate space prediction for improved 3D object understanding.

Findings

Effective in estimating shape and pose on synthetic datasets

Accurate metric scale and position in real-world scenarios

Outperforms existing category-level pose estimation methods

Abstract

Advances in deep learning recognition have led to accurate object detection with 2D images. However, these 2D perception methods are insufficient for complete 3D world information. Concurrently, advanced 3D shape estimation approaches focus on the shape itself, without considering metric scale. These methods cannot determine the accurate location and orientation of objects. To tackle this problem, we propose a framework that jointly estimates a metric scale shape and pose from a single RGB image. Our framework has two branches: the Metric Scale Object Shape branch (MSOS) and the Normalized Object Coordinate Space branch (NOCS). The MSOS branch estimates the metric scale shape observed in the camera coordinates. The NOCS branch predicts the normalized object coordinate space (NOCS) map and performs similarity transformation with the rendered depth map from a predicted metric scale mesh to obtain 6d pose and size. Additionally, we introduce the Normalized Object Center Estimation (NOCE) to estimate the geometrically aligned distance from the camera to the object center. We validated our method on both synthetic and real-world datasets to evaluate category-level object pose and shape.