Related papers: Segmenting Unknown 3D Objects from Real Depth Imag…

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

This paper proposes a deep neural architecture, PlaneRCNN, that detects and reconstructs piecewise planar surfaces from a single RGB image. PlaneRCNN employs a variant of Mask R-CNN to detect planes with their plane parameters and…

As capturing devices become common, 3D scans of interior spaces are acquired on a daily basis. Through scene comparison over time, information about objects in the scene and their changes is inferred. This information is important for…

Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object…

Fine-grained categorization can benefit from part-based features which reveal subtle visual differences between object categories. Handcrafted features have been widely used for part detection and classification. Although a recent trend…

Grasping skill is a major ability that a wide number of real-life applications require for robotisation. State-of-the-art robotic grasping methods perform prediction of object grasp locations based on deep neural networks. However, such…

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

Deep Neural Networks (DNNs) based semantic segmentation of the robotic instruments and tissues can enhance the precision of surgical activities in robot-assisted surgery. However, in biological learning, DNNs cannot learn incremental tasks…

The ability to localize and segment objects from unseen classes would open the door to new applications, such as autonomous object learning in active vision. Nonetheless, improving the performance on unseen classes requires additional…

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation…

We propose a new method to count objects of specific categories that are significantly smaller than the ground sampling distance of a satellite image. This task is hard due to the cluttered nature of scenes where different object categories…

In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they…

Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…

To be useful in everyday environments, robots must be able to observe and learn about objects. Recent datasets enable progress for classifying data into known object categories; however, it is unclear how to collect reliable object data…

Instance segmentation is a fundamental skill for many robotic applications. We propose a self-supervised method that uses grasp interactions to collect segmentation supervision for an instance segmentation model. When a robot grasps an…

Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more…

Most computer vision research focuses on datasets containing thousands of images of commonplace objects. However, many high-impact datasets, such as those in medicine and the geosciences, contain fine-grain objects that require…

Image compression is a critical tool in decreasing the cost of storage and improving the speed of transmission over the internet. While deep learning applications for natural images widely adopts the usage of lossy compression techniques,…

The standard approach to tackling computer vision problems is to train deep convolutional neural network (CNN) models using large-scale image datasets which are representative of the target task. However, in many scenarios, it is often…

Recently, there has been a high demand for accelerating and improving the detection of automatic cadastral mapping. As this problem is in its starting point, there are many methods of computer vision and deep learning that have not been…