Related papers: Multi-View Deep Learning for Consistent Semantic M…

The goal of our work is to complete the depth channel of an RGB-D image. Commodity-grade depth cameras often fail to sense depth for shiny, bright, transparent, and distant surfaces. To address this problem, we train a deep network that…

We study the task of embodied visual active learning, where an agent is set to explore a 3d environment with the goal to acquire visual scene understanding by actively selecting views for which to request annotation. While accurate on some…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…

Multi-view clustering has attracted increasing attentions recently by utilizing information from multiple views. However, existing multi-view clustering methods are either with high computation and space complexities, or lack of…

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic…

Although well-known large-scale datasets, such as ImageNet, have driven image understanding forward, most of these datasets require extensive manual annotation and are thus not easily scalable. This limits the advancement of image…

Simultaneous Localization and Mapping (SLAM) is one of the most essential techniques in many real-world robotic applications. The assumption of static environments is common in most SLAM algorithms, which however, is not the case for most…

Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or…

This paper presents SceneCut, a novel approach to jointly discover previously unseen objects and non-object surfaces using a single RGB-D image. SceneCut's joint reasoning over scene semantics and geometry allows a robot to detect and…

Visual slam technology is one of the key technologies for robot to explore unknown environment independently. Accurate estimation of camera pose based on visual sensor is the basis of autonomous navigation and positioning. However, most…

In this work, we develop a monocular SLAM-aware object recognition system that is able to achieve considerably stronger recognition performance, as compared to classical object recognition systems that function on a frame-by-frame basis. By…

Depth is a very important modality in computer vision, typically used as complementary information to RGB, provided by RGB-D cameras. In this work, we show that it is possible to obtain the same level of accuracy as RGB-D cameras on a…

Visual SLAM (Simultaneous Localization and Mapping) methods typically rely on handcrafted visual features or raw RGB values for establishing correspondences between images. These features, while suitable for sparse mapping, often lead to…

Deep learning approaches have achieved highly accurate face recognition by training the models with very large face image datasets. Unlike the availability of large 2D face image datasets, there is a lack of large 3D face datasets available…

Current techniques in Visual Simultaneous Localization and Mapping (VSLAM) estimate camera displacement by comparing image features of consecutive scenes. These algorithms depend on scene continuity, hence requires frequent camera inputs.…

Stairs are common building structures in urban environments, and stair detection is an important part of environment perception for autonomous mobile robots. Most existing algorithms have difficulty combining the visual information from…

In this paper, we propose a new correlated and individual multi-modal deep learning (CIMDL) method for RGB-D object recognition. Unlike most conventional RGB-D object recognition methods which extract features from the RGB and depth…

Geometric navigation is nowadays a well-established field of robotics and the research focus is shifting towards higher-level scene understanding, such as Semantic Mapping. When a robot needs to interact with its environment, it must be…

Most deep learning approaches to comprehensive semantic modeling of 3D indoor spaces require costly dense annotations in the 3D domain. In this work, we explore a central 3D scene modeling task, namely, semantic scene reconstruction without…