Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks. However, this increase in performance requires large scale annotations of 2D/3D data. In this paper, we explore inexpensive 2D supervision as an alternative for expensive 3D CAD annotation. Specifically, we use foreground masks as weak supervision through a raytrace pooling layer that enab...

Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2). The network learns a mapping from images of objects to their underlying 3D shapes from a large collection of synthetic data [13]. Our network takes in one or more i...

Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks. However, this increase in performance requires large scale annotations of 2D/3D data. In this paper, we explore inexpensive 2D supervision as an alternative for expensive 3D CAD annotation. Specifically, we use foreground masks as weak supervision through a raytrace pooling layer that enab...

3D reconstruction of geo-objects from their digital images is a time-efficient and convenient way of studying the structural features of the object being modelled. This paper presents a 3D reconstruction methodology which can be used to generate photo-realistic 3D watertight surface of different irregular shaped objects, from digital image sequences of the objects. The 3D reconstruction approac...

Although an image is a 2D array, we live in a 3D world. The desire to recover the 3D structure of the world from 2D images is the key that distinguished computer vision from the already existing field of image processing 50 years ago. For the past two decades, the dominant research focus for 3D reconstruction is in obtaining more accurate depth maps or 3D point clouds. However, even when a robo...

Camera calibration is an important and sensitive step in 3D environment reconstruction by stereovision. Small errors in the estimation of the camera parameters could rise to high errors in the 3D measurements, as the working distance increases. Therefore a method for analyzing the influence of each camera’s parameter error in the accuracy of the 3D measurement is compulsory in order to minimize...

3D reconstructions from photographs often exhibit poor robustness and global consistency. This is a problem in applications such as model acquisition and registration where global consistency is needed to ensure that the reconstruction looks acceptable from all views. Our goal is to develop a robust reconstruction approach which leads to better consistency between viewpoints. We do this by solv...

We describe an automatic technique for segmenting the outer cortical surface from axial MR images. The scalp outline defines a search area within which the cortex can be expected to lie. The image is sampled radially and a special purpose edge-detector is used to create an initial estimate of the cortical surface. This estimate is then relaxed under the control of local edge constraints. The co...

We present a simple and intuitive method for interactive 3D reconstruction and camera calibration from a single image of a structured scene. The method is based on manual registration of two world planes. We present experimental results on some test images.

This paper deals with the problem of error estimation in 3D reconstruction. It shows how interval analysis can be used in this way for 3D vision applications. The description of an image point by an interval assumes an unknown but bounded localization. We present a new method based on interval analysis tools to propagate this bounded uncertainty. This way of computation can produce guaranteed r...