3D Object Detection and Viewpoint Estimation with a Deformable 3D Cuboid Model
published: Jan. 14, 2013, recorded: December 2012, views: 6415
Slides
Related content
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Description
This paper addresses the problem of category-level 3D object detection. Given a monocular image, our aim is to localize the objects in 3D by enclosing them with tight oriented 3D bounding boxes. We propose a novel approach that extends the well-acclaimed deformable part-based model[Felz.] to reason in 3D. Our model represents an object class as a deformable 3D cuboid composed of faces and parts, which are both allowed to deform with respect to their anchors on the 3D box. We model the appearance of each face in fronto-parallel coordinates, thus effectively factoring out the appearance variation induced by viewpoint. Our model reasons about face visibility patters called aspects. We train the cuboid model jointly and discriminatively and share weights across all aspects to attain efficiency. Inference then entails sliding and rotating the box in 3D and scoring object hypotheses. While for inference we discretize the search space, the variables are continuous in our model. We demonstrate the effectiveness of our approach in indoor and outdoor scenarios, and show that our approach outperforms the state-of-the-art in both 2D[Felz09] and 3D object detection[Hedau12].
See Also:
Download slides:
machine_fidler_object_detection_01.pdf (8.6 MB)
Download article:
machine_fidler_object_detection_01.pdf (1.0 MB)
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
Reviews and comments:
This paper presents a novel approach for category-level 3D object detection, extending the deformable part-based model to reason in 3D. The proposed deformable 3D cuboid model allows for flexible representation of object classes, with deformable faces and parts. By modeling appearance in fronto-parallel coordinates, viewpoint-induced variation is factored out. Joint and discriminative training, along with weight sharing, enhances efficiency. The method achieves superior performance in both indoor and outdoor scenarios, outperforming state-of-the-art methods in both 2D and 3D object detection.
https://games.lol/figgerits/
https://www.emulatorpc.com/fun-hospital/
Write your own review or comment: