3D object recognition is the task of recognising objects from 3D data.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders.
In this work, each object is represented using a set of general latent visual topics and category-specific dictionaries.
In this paper we propose a neural message passing approach to augment an input 3D indoor scene with new objects matching their surroundings.
Finally, we propose the best cluster numbers for each class of objects in KITTI dataset that improves the performance of detection model significantly.
In this paper, we therefore propose a loss to specifically address the hubness problem.
Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision.
Experimental results on ModelNet10 and ModelNet40 datasets show that our MV-C3D technique can achieve outstanding performance with multi-view images which are captured from partial angles with less range.
Depth perception is a key component for autonomous systems that interact in the real world, such as delivery robots, warehouse robots, and self-driving cars.