Related papers: Scene Coordinate Regression with Angle-Based Repro…
The goal of this work is to replace objects in an RGB-D scene with corresponding 3D models from a library. We approach this problem by first detecting and segmenting object instances in the scene using the approach from Gupta et al. [13].…
We apply convolutional neural networks (CNN) to the problem of image orientation detection in the context of determining the correct orientation (from 0, 90, 180, and 270 degrees) of a consumer photo. The problem is especially important for…
This work presents a novel Convolutional Neural Network (CNN) architecture and a training procedure to enable robust and accurate pose estimation of a noncooperative spacecraft. First, a new CNN architecture is introduced that has scored a…
This paper addresses the problem of 3D human pose estimation from single images. While for a long time human skeletons were parameterized and fitted to the observation by satisfying a reprojection error, nowadays researchers directly use…
In this paper, we propose a novel approach that learns to sequentially attend to different Convolutional Neural Networks (CNN) layers (i.e., ``what'' feature abstraction to attend to) and different spatial locations of the selected feature…
Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can be used online, the former often fail away from the training…
Global visual localization estimates the absolute pose of a camera using a single image, in a previously mapped area. Obtaining the pose from a single image enables many robotics and augmented/virtual reality applications. Inspired by…
Many machine learning methods operate by inverting a neural network at inference time, which has become a popular technique for solving inverse problems in computer vision, robotics, and graphics. However, these methods often involve…
Thesedays, Convolutional Neural Networks are widely used in semantic segmentation. However, since CNN-based segmentation networks produce low-resolution outputs with rich semantic information, it is inevitable that spatial details (e.g.,…
This paper presents a study on the use of Convolutional Neural Networks for camera relocalisation and its application to map compression. We follow state of the art visual relocalisation results and evaluate the response to different data…
Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets.…
While 360{\deg} cameras offer tremendous new possibilities in vision, graphics, and augmented reality, the spherical images they produce make core feature extraction non-trivial. Convolutional neural networks (CNNs) trained on images from…
Recently, CNN is a popular choice to handle the hyperspectral image classification challenges. In spite of having such large spectral information in Hyper-Spectral Image(s) (HSI), it creates a curse of dimensionality. Also, large spatial…
Deep learning has been applied to camera relocalization, in particular, PoseNet and its extended work are the convolutional neural networks which regress the camera pose from a single image. However there are many problems, one of them is…
Scene coordinate regression (SCR) models have proven to be powerful implicit scene representations for 3D vision, enabling visual relocalization and structure-from-motion. SCR models are trained specifically for one scene. If training…
Learning-based visual relocalizers exhibit leading pose accuracy, but require hours or days of training. Since training needs to happen on each new scene again, long training times make learning-based relocalization impractical for most…
This work investigates the impact of the loss function on the performance of Neural Networks, in the context of a monocular, RGB-only, image localization task. A common technique used when regressing a camera's pose from an image is to…
We address the problem of camera pose estimation in visual localization. Current regression-based methods for pose estimation are trained and evaluated scene-wise. They depend on the coordinate frame of the training dataset and show a low…
Scene coordinates regression (SCR), i.e., predicting 3D coordinates for every pixel of a given image, has recently shown promising potential. However, existing methods remain limited to small scenes memorized during training, and thus…
In this paper, we present a new approach for improving 3D point and line mapping regression for camera re-localization. Previous methods typically rely on feature matching (FM) with stored descriptors or use a single network to encode both…