Deep Cuboid Detection: Beyond 2D Bounding Boxes
arXiv:1611.10010
Abstract
We present a Deep Cuboid Detector which takes a consumer-quality RGB image of a cluttered scene and localizes all 3D cuboids (box-like objects). Contrary to classical approaches which fit a 3D model from low-level cues like corners, edges, and vanishing points, we propose an end-to-end deep learning system to detect cuboids across many semantic categories (e.g., ovens, shipping boxes, and furniture). We localize cuboids with a 2D bounding box, and simultaneously localize the cuboid's corners, effectively producing a 3D interpretation of box-like objects. We refine keypoints by pooling convolutional features iteratively, improving the baseline method significantly. Our deep learning cuboid detector is trained in an end-to-end fashion and is suitable for real-time applications in augmented reality (AR) and robotics.
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Human pose estimation via Convolutional Part Heatmap Regression
- Rich feature hierarchies for accurate object detection and semantic segmentation
- Deep Image Homography Estimation
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images
- Inferring 3D Object Pose in RGB-D Images
- Viewpoints and Keypoints
Cited by in corpus (4)
- 6D Pose Estimation with Combined Deep Learning and 3D Vision Techniques for a Fast and Accurate Object Grasping
- Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
- AutoSweep: Recovering 3D Editable Objectsfrom a Single Photograph
- Geometry-constrained Car Recognition Using a 3D Perspective Network