☆ 4.6 Article

SDFEst: Categorical Pose and Shape Estimation of Objects From RGB-D Using Signed Distance Fields

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

iCaps: Iterative Category-Level Object Pose and Shape Estimation

Xinke Deng et al.

Summary: This letter proposes a category-level 6D object pose and shape estimation approach iCaps, which allows tracking and estimating the poses and shapes of unseen objects. It achieves this by using a category-level auto-encoder network and LatentNet.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

Xian-Feng Han et al.

Summary: This article provides a comprehensive survey of recent developments in image-based 3D reconstruction using convolutional neural networks, focusing on estimating the 3D shape of generic objects from single or multiple RGB images. The survey analyzes and compares the performance of key papers, summarizes open problems in the field, and discusses promising directions for future research.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Robotics

MOLTR: Multiple Object Localization, Tracking and Reconstruction From Monocular RGB Videos

Kejie Li et al.

Summary: Semantic aware reconstruction provides more advantages for future robotic and AR/VR applications compared to geometric-only reconstruction, as it not only indicates the locations of objects, but also identifies the objects themselves. MOLTR is capable of localizing, tracking, and reconstructing multiple rigid objects using monocular image sequences and camera poses.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence