2014 Poster Sessions : Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild

Student Name : Yu Xiang
Advisor : Silvio Savarese
Research Areas: Artificial Intelligence
3D object detection and pose estimation methods have become popular in recent years since they can handle ambiguities in 2D images and also provide a richer description for objects compared to 2D object detectors. However, most of the datasets for 3D recognition are limited to a small amount of images per category or are captured in controlled environments. In this paper, we contribute PASCAL3D+ dataset, which is a novel and challenging dataset for 3D object detection and pose estimation. PASCAL3D+ augments 12 rigid categories of the PASCAL VOC 2012 with 3D annotations. Furthermore, more images are added for each category from ImageNet. PASCAL3D+ images exhibit much more variability compared to the existing 3D datasets, and on average there are more than 3,000 object instances per category. We believe this dataset will provide a rich testbed to study 3D detection and pose estimation and will help to significantly push forward research in this area. We provide the results of variations of DPM on our new dataset for object detection and viewpoint estima tion in different scenarios, which can be used as baselines for the community. Our benchmark is available online at http://cvgl.stanford.edu/projects/pascal3d

Yu Xiang is a Phd student in the Electrical Engineering and Computer Science Department at the University of Michigan. Yu joined the computer vision lab at the University of Michigan in 2010. His advisor is Prof. Silvio Savarese. Yu's research focuses on understanding objects and scenes from images and videos, with emphasis on recognizing both semantic and 3D geometric properties of objects and scenes. His current work attempts to develop 3D object representation and recognition methods which can be useful for real world applications. Yu received his B.S. degree in computer science from Fudan University in 2007 and his M.S. degree in computer science from Fudan University in 2010. Yu did research on automatic image annotation under the supervision of Prof. Xiangdong Zhou for his master thesis.