Inferring 3D Object Pose in RGB-D Images

Abstract

The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13]. We use a convolutional neural network (CNN) to predict the pose of the object. This CNN is trained using pixel normals in images containing rendered synthetic objects. When tested on real data, it outperforms alternative algorithms trained on real data. We then use this coarse pose estimate along with the inferred pixel support to align a small number of prototypical models to the data, and place the model that fits the best into the scene. We observe a 48% relative improvement in performance at the task of 3D detection over the current state-of-the-art [33], while being an order of magnitude faster at the same time.

arXiv comment13 pages, 8 figures, 4 tables

References in corpus (2)

• Rich feature hierarchies for accurate object detection and semantic segmentation
• Simultaneous Detection and Segmentation

Cited by in corpus (6)

• Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
• Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Images
• Deep Cuboid Detection: Beyond 2D Bounding Boxes
• Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing
• PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning
• iSPA-Net: Iterative Semantic Pose Alignment Network