Category-Level Metric Scale Object Shape and Pose Estimation

نویسندگان

چکیده

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

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A New Metric for Object Pose Estimation

Object pose estimation is a difficult task due to the non-linearities of the projection process; specifically with regard to the effect of depth. To overcome this complication, most algorithms use an error metric which removes the effect of depth. Recently, two new algorithms have been proposed based upon iteratively improving pose estimates obtained with weak-perspective or paraperspective app...

متن کامل

Joint Object Category and 3D Pose Estimation from 2D Images

2D object detection is the task of finding (i) what objects are present in an image and (ii) where they are located, while 3D pose estimation is the task of finding the pose of these objects in 3D space. State-of-the-art methods for solving these tasks follow a two-stage approach where a 3D pose estimation system is applied to bounding boxes (with associated category labels) returned by a 2D de...

متن کامل

Physics-Based Object Pose and Shape Estimation from Multiple Views

This paper presents a new algorithm for object pose and shape estimation from multiple views. Using a qualitative shape recovery scheme we first segment the image into parts which belong to a vocabulary of primitives. Based on the additional constraints provided by the qualitative shapes we extend our physics-based framework to allow object pose and shape estimation from stereo images where the...

متن کامل

Joint Object Pose Estimation and Shape Reconstruction in Urban Street Scenes Using 3D Shape Priors

Estimating the pose and 3D shape of a large variety of instances within an object class from stereo images is a challenging problem, especially in realistic conditions such as urban street scenes. We propose a novel approach for using compact shape manifolds of the shape within an object class for object segmentation, pose and shape estimation. Our method first detects objects and estimates the...

متن کامل

Object recognition using metric shape

Most previous studies of 3D shape perception have shown a general inability to visually perceive metric shape. In line with this, studies of object recognition have shown that only qualitative differences, not quantitative or metric ones can be used effectively for object recognition. Recently, Bingham and Lind (2008) found that large perspective changes (≥ 45°) allow perception of metric shape...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE robotics and automation letters

سال: 2021

ISSN: ['2377-3766']

DOI: https://doi.org/10.1109/lra.2021.3110538