Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
Top Cited Papers
- 1 December 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2686-2694
- https://doi.org/10.1109/iccv.2015.308
Abstract
Object viewpoint estimation from 2D images is an essential task in computer vision. However, two issues hinder its progress: scarcity of training data with viewpoint annotations, and a lack of powerful features. Inspired by the growing availability of 3D models, we propose a framework to address both issues by combining render-based image synthesis and CNNs (Convolutional Neural Networks). We believe that 3D models have the potential in generating a large number of images of high variation, which can be well exploited by deep CNN with a high learning capacity. Towards this goal, we propose a scalable and overfit-resistant image synthesis pipeline, together with a novel CNN specifically tailored for the viewpoint estimation task. Experimentally, we show that the viewpoint estimation from our pipeline can significantly outperform state-of-the-art methods on PASCAL 3D+ benchmark.Keywords
This publication has 26 references indexed in Scilit:
- Joint embeddings of shapes and images via CNN image purificationACM Transactions on Graphics, 2015
- Viewpoints and keypointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Beyond PASCAL: A benchmark for 3D object detection in the wildPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- SUN database: Large-scale scene recognition from abbey to zooPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Multi-view object class detection with a 3D geometric modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Back to the Future: Learning Shape Models from 3D CAD DataPublished by British Machine Vision Association and Society for Pattern Recognition ,2010
- Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Free-form deformation of solid geometric modelsPublished by Association for Computing Machinery (ACM) ,1986
- The singularities of the visual mappingBiological Cybernetics, 1976