Related papers: Adaptive Continuous Visual Odometry from RGB-D Ima…

Purpose: In this paper, we present a novel approach to the automatic evaluation of open surgery skills using depth cameras. This work is intended to show that depth cameras achieve similar results to RGB cameras, which is the common method…

We propose a dense dynamic RGB-D SLAM pipeline based on a learning-based visual odometry, TartanVO. TartanVO, like other direct methods rather than feature-based, estimates camera pose through dense optical flow, which only applies to…

Image acquisition in low-light conditions suffers from poor quality and significant degradation in visual aesthetics. This affects the visual perception of the acquired image and the performance of various computer vision and image…

We introduce a novel method to automatically adjust camera exposure for image processing and computer vision applications on mobile robot platforms. Because most image processing algorithms rely heavily on low-level image features that are…

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…

Digital images nowadays have various styles of appearance, in the aspects of color tones, contrast, vignetting, and etc. These 'picture styles' are directly related to the scene radiance, image pipeline of the camera, and post processing…

Visual scene understanding is an important capability that enables robots to purposefully act in their environment. In this paper, we propose a novel approach to object-class segmentation from multiple RGB-D views using deep learning. We…

Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving…

This article describes an algorithm that provides visual odometry estimates from sequential pairs of RGBD images. The key contribution of this article on RGBD odometry is that it provides both an odometry estimate and a covariance for the…

Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry (VO) and simultaneous localization and mapping (SLAM), where classic methods consisting of hand-crafted features and sampling-based outlier…

We propose a novel algorithm for the fitting of 3D human shape to images. Combining the accuracy and refinement capabilities of iterative gradient-based optimization techniques with the robustness of deep neural networks, we propose a…

In video-based action recognition, viewpoint variations often pose major challenges because the same actions can appear different from different views. We use the complementary RGB and Depth information from the RGB-D cameras to address…

Monocular visual odometry (VO) is an important task in robotics and computer vision. Thus far, how to build accurate and robust monocular VO systems that can work well in diverse scenarios remains largely unsolved. In this paper, we propose…

General object grasping is an important yet unsolved problem in the field of robotics. Most of the current methods either generate grasp poses with few DoF that fail to cover most of the success grasps, or only take the unstable depth image…

Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D…

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 present a method for temporally consistent motion segmentation from RGB-D videos assuming a piecewise rigid motion model. We formulate global energies over entire RGB-D sequences in terms of the segmentation of each frame into a number…

Accurate scale estimation of a target is a challenging research problem in visual object tracking. Most state-of-the-art methods employ an exhaustive scale search to estimate the target size. The exhaustive search strategy is…

We present a method to infer a dense depth map from a color image and associated sparse depth measurements. Our main contribution lies in the design of an annealing process for determining co-visibility (occlusions, disocclusions) and the…

We address the problem of text-guided video temporal grounding, which aims to identify the time interval of a certain event based on a natural language description. Different from most existing methods that only consider RGB images as…