Aligning 3D models to RGB-D images of cluttered scenes
- 1 June 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4731-4740
- https://doi.org/10.1109/cvpr.2015.7299105
Abstract
The goal of this work is to represent 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 and then using a convolutional neural network (CNN) to predict the pose of the object. This CNN is trained using pixel surface normals in images containing renderings of synthetic objects. When tested on real data, our method 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 into the scene the model that fits best. We observe a 48% relative improvement in performance at the task of 3D detection over the current state-of-the-art [34], while being an order of magnitude faster.Keywords
This publication has 20 references indexed in Scilit:
- Scene Parsing with Object Instances and Occlusion OrderingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- What Are You Talking About? Text-to-Image CoreferencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Learning hierarchical sparse features for RGB-(D) object recognitionThe International Journal of Robotics Research, 2014
- Instance Segmentation of Indoor Scenes Using a Coverage LossLecture Notes in Computer Science, 2014
- Box in the Box: Joint 3D Layout and Object Reasoning from Single ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Perceptual Organization and Recognition of Indoor Scenes from RGB-D ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- A Category-Level 3D Object Dataset: Putting the Kinect to WorkPublished by Springer Science and Business Media LLC ,2013
- An interactive approach to semantic modeling of indoor scenes with an RGBD cameraACM Transactions on Graphics, 2012
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Efficient variants of the ICP algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002