Stereo Object Matching Network

This paper presents a stereo object matching method that exploits both 2D contextual information from images as well as 3D object-level information. Unlike existing stereo matching methods that exclusively focus on the pixel-level correspondence between stereo images within a volumetric space (i. e. , cost volume), we exploit this volumetric structure in a different manner. The cost volume explicitly encompasses 3D information along its disparity axis, therefore it is a privileged structure that can encapsulate the 3D contextual information from objects. However, it is not straightforward since the disparity values map the 3D metric space in a non-linear fashion. Thus, we present two novel strategies to handle 3D objectness in the cost volume space: selective sampling (RoISelect) and 2D-3D fusion (fusion-by-occupancy), which allow us to seamlessly incorporate 3D object-level information and achieve accurate depth performance near the object boundary regions. Our depth estimation achieves competitive performance in the KITTI dataset and the Virtual-KITTI 2. 0 dataset.

Authors

• Jaesung Choe
• Kyungdon Joo
• François Rameau
• In-So Kweon

Keywords

• Measurement
• Three-dimensional displays
• Costs
• Automation
• Conferences
• Estimation
• Object detection
• Matching Network
• Contextual Information
• 3D Space
• 3D Information
• Depth Estimation
• Object Boundaries
• Stereo Images
• KITTI Dataset
• Disparity Values
• Stereo Matching
• Cost Volume
• Ambiguity
• Convolutional Neural Network
• 3D Structure
• Image Features
• Feature Maps
• Receptive Field
• Semantic Segmentation
• Object Location
• 3D Object Detection
• 3D Detection
• Auxiliary Task
• Disparity Map
• Head Network
• Disparity Estimation
• Deep Learning-based Approaches
• Matching Cost
• Cost Aggregation
• 2D Information