相关论文: DFNet: Enhance Absolute Pose Regression with Direc…

Camera pose estimation is an important problem in computer vision. Common techniques either match the current image against keyframes with known poses, directly regress the pose, or establish correspondences between keypoints in the image…

Deep generative models have made great progress in synthesizing images with arbitrary human poses and transferring poses of one person to others. Though many different methods have been proposed to generate images with high visual fidelity,…

Differentiable rendering aims to compute the derivative of the image rendering function with respect to the rendering parameters. This paper presents a novel algorithm for 6-DoF pose estimation through gradient-based optimization using a…

We propose a novel image based localization system using graph neural networks (GNN). The pretrained ResNet50 convolutional neural network (CNN) architecture is used to extract the important features for each image. Following, the extracted…

We introduce FocalPose, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are twofold. First,…

Robotic systems often require precise scene analysis capabilities, especially in unstructured, cluttered situations, as occurring in human-made environments. While current deep-learning based methods yield good estimates of object poses,…

We introduce CenDerNet, a framework for 6D pose estimation from multi-view images based on center and curvature representations. Finding precise poses for reflective, textureless objects is a key challenge for industrial robotics. Our…

Solving the camera-to-robot pose is a fundamental requirement for vision-based robot control, and is a process that takes considerable effort and cares to make accurate. Traditional approaches require modification of the robot via markers,…

Many real-world 3D reconstruction applications demand photorealism and metric accuracy across unbounded, complex scenes with challenging lighting and imperfect captures that current Neural Radiance Field (NeRF) pipelines only partly…

Precise 6D pose estimation of rigid objects from RGB images is a critical but challenging task in robotics, augmented reality and human-computer interaction. To address this problem, we propose DeepRM, a novel recurrent network architecture…

Establishing robust and accurate correspondences between a pair of images is a long-standing computer vision problem with numerous applications. While classically dominated by sparse methods, emerging dense approaches offer a compelling…

This paper proposes a novel learning based high-dynamic-range (HDR) reconstruction method using a polarization camera. We utilize a previous observation that polarization filters with different orientations can attenuate natural light…

Multi-view facial expression recognition (FER) is a challenging task because the appearance of an expression varies in poses. To alleviate the influences of poses, recent methods either perform pose normalization or learn separate FER…

In this paper we propose a framework for integrating map-based relocalization into online direct visual odometry. To achieve map-based relocalization for direct methods, we integrate image features into Direct Sparse Odometry (DSO) and rely…

Convolutional neural networks (CNNs) and transfer learning have recently been used for 6 degrees of freedom (6-DoF) camera pose estimation. While they do not reach the same accuracy as visual SLAM-based approaches and are restricted to a…

Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of…

This paper presents a novel algorithm named Direct Simultaneous Registration (DSR) that registers a collection of 3D images in a simultaneous fashion without specifying any reference image, feature extraction and matching, or information…

Most existing methods for CRF estimation from a single image fail to handle general real images. For instance, EdgeCRF based on colour patches extracted from edges works effectively only when the presence of noise is insignificant, which is…

Localization of anatomical landmarks is essential for clinical diagnosis, treatment planning, and research. In this paper, we propose a novel deep network, named feature aggregation and refinement network (FARNet), for the automatic…

This paper addresses the problem of estimating the 3-DoF camera pose for a ground-level image with respect to a satellite image that encompasses the local surroundings. We propose a novel end-to-end approach that leverages the learning of…