2017 IEEE International Conference on Computer Vision (ICCV)

22-29 Oct. 2017

Filter Results

Displaying Results 1 - 25 of 632
  • [Title page i]

    Publication Year: 2017, Page(s): i
    Request permission for commercial reuse | |PDF file iconPDF (96 KB)
    Freely Available from IEEE
  • [Title page iii]

    Publication Year: 2017, Page(s): iii
    Request permission for commercial reuse | |PDF file iconPDF (132 KB)
    Freely Available from IEEE
  • [Copyright notice]

    Publication Year: 2017, Page(s): iv
    Request permission for commercial reuse | |PDF file iconPDF (114 KB)
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2017, Page(s):v - xlii
    Request permission for commercial reuse | |PDF file iconPDF (213 KB)
    Freely Available from IEEE
  • Message from the General Chairs

    Publication Year: 2017, Page(s): xliii
    Request permission for commercial reuse | |PDF file iconPDF (67 KB)
    Freely Available from IEEE
  • Message from the Program Chairs

    Publication Year: 2017, Page(s):xliv - xlvii
    Request permission for commercial reuse | |PDF file iconPDF (79 KB)
    Freely Available from IEEE
  • Organizing Committee

    Publication Year: 2017, Page(s): xlviii
    Request permission for commercial reuse | |PDF file iconPDF (49 KB)
    Freely Available from IEEE
  • Area Chairs

    Publication Year: 2017, Page(s): xlvix
    Request permission for commercial reuse | |PDF file iconPDF (196 KB)
    Freely Available from IEEE
  • 2017 Outstanding and Emergency Reviewers

    Publication Year: 2017, Page(s): l
    Request permission for commercial reuse | |PDF file iconPDF (41 KB)
    Freely Available from IEEE
  • Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence

    Publication Year: 2017, Page(s):1 - 10
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (952 KB) | HTML iconHTML

    Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications. Perspective-n-Point (PnP) solvers are routinely used for camera pose estimation, provided that a good quality set of 2D-3D feature correspondences are known beforehand. However, finding optimal correspondences between 2D key-points and a 3D p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Pseudo Random Fields for Light-Field Stereo Matching

    Publication Year: 2017, Page(s):11 - 19
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1810 KB) | HTML iconHTML

    Markov Random Fields are widely used to model lightfield stereo matching problems. However, most previous approaches used fixed parameters and did not adapt to lightfield statistics. Instead, they explored explicit vision cues to provide local adaptability and thus enhanced depth quality. But such additional assumptions could end up confining their applicability, e.g. algorithms designed for dense... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Lightweight Approach for On-the-Fly Reflectance Estimation

    Publication Year: 2017, Page(s):20 - 28
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2100 KB) | HTML iconHTML

    Estimating surface reflectance (BRDF) is one key component for complete 3D scene capture, with wide applications in virtual reality, augmented reality, and human computer interaction. Prior work is either limited to controlled environments (e.g., gonioreflectometers, light stages, or multi-camera domes), or requires the joint optimization of shape, illumination, and reflectance, which is often com... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distributed Very Large Scale Bundle Adjustment by Global Camera Consensus

    Publication Year: 2017, Page(s):29 - 38
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (642 KB) | HTML iconHTML

    The increasing scale of Structure-from-Motion is fundamentally limited by the conventional optimization framework for the all-in-one global bundle adjustment. In this paper, we propose a distributed approach to coping with this global bundle adjustment for very large scale Structure-from-Motion computation. First, we derive the distributed formulation from the classical optimization algorithm ADMM... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Practical Projective Structure from Motion (P2SfM)

    Publication Year: 2017, Page(s):39 - 47
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1607 KB) | HTML iconHTML

    This paper presents a solution to the Projective Structure from Motion (PSfM) problem able to deal efficiently with missing data, outliers and, for the first time, large scale 3D reconstruction scenarios. By embedding the projective depths into the projective parameters of the points and views, we decrease the number of unknowns to estimate and improve computational speed by optimizing standard li... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Anticipating Daily Intention Using On-wrist Motion Triggered Sensing

    Publication Year: 2017, Page(s):48 - 56
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (957 KB) | HTML iconHTML

    Anticipating human intention by observing one's actions has many applications. For instance, picking up a cellphone, then a charger (actions) implies that one wants to charge the cellphone (intention) (Fig. 1). By anticipating the intention, an intelligent system can guide the user to the closest power outlet. We propose an on-wrist motion triggered sensing system for anticipating daily intentions... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rethinking Reprojection: Closing the Loop for Pose-Aware Shape Reconstruction from a Single Image

    Publication Year: 2017, Page(s):57 - 65
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (914 KB) | HTML iconHTML

    An emerging problem in computer vision is the reconstruction of 3D shape and pose of an object from a single image. Hitherto, the problem has been addressed through the application of canonical deep learning methods to regress from the image directly to the 3D shape and pose labels. These approaches, however, are problematic from two perspectives. First, they are minimizing the error between 3D sh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • End-to-End Learning of Geometry and Context for Deep Stereo Regression

    Publication Year: 2017, Page(s):66 - 75
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1720 KB) | HTML iconHTML

    We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem's geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using Sparse Elimination for Solving Minimal Problems in Computer Vision

    Publication Year: 2017, Page(s):76 - 84
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (297 KB) | HTML iconHTML

    Finding a closed form solution to a system of polynomial equations is a common problem in computer vision as well as in many other areas of engineering and science. Gröbner basis techniques are often employed to provide the solution, but implementing an efficient Gröbner basis solver to a given problem requires strong expertise in algebraic geometry. One can also convert the equati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

    Publication Year: 2017, Page(s):85 - 93
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1146 KB) | HTML iconHTML

    We propose a data-driven method for recovering missing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network. The global structure inference network incorporates a long short-term memorized context fusion module (LSTM-CF) that infers the global structure of the shape b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal Tessellation: A Unified Approach for Video Analysis

    Publication Year: 2017, Page(s):94 - 104
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (1242 KB) | HTML iconHTML

    We present a general approach to video understanding, inspired by semantic transfer techniques that have been successfully used for 2D image analysis. Our method considers a video to be a 1D sequence of clips, each one associated with its own semantics. The nature of these semantics - natural language captions or other labels - depends on the task at hand. A test video is processed by forming corr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning Policies for Adaptive Tracking with Deep Feature Cascades

    Publication Year: 2017, Page(s):105 - 114
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (587 KB)

    Visual object tracking is a fundamental and time-critical vision task. Recent years have seen many shallow tracking methods based on real-time pixel-based correlation filters, as well as deep methods that have top performance but need a high-end GPU. In this paper, we learn to improve the speed of deep trackers without losing accuracy. Our fundamental insight is to take an adaptive approach, where... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Temporal Shape Super-Resolution by Intra-frame Motion Encoding Using High-fps Structured Light

    Publication Year: 2017, Page(s):115 - 123
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (2239 KB) | HTML iconHTML

    One of the solutions of depth imaging of moving scene is to project a static pattern on the object and use just a single image for reconstruction. However, if the motion of the object is too fast with respect to the exposure time of the image sensor, patterns on the captured image are blurred and reconstruction fails. In this paper, we impose multiple projection patterns into each single captured ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-Time Monocular Pose Estimation of 3D Objects Using Temporally Consistent Local Color Histograms

    Publication Year: 2017, Page(s):124 - 132
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (4663 KB) | HTML iconHTML

    We present a novel approach to 6DOF pose estimation and segmentation of rigid 3D objects using a single monocular RGB camera based on temporally consistent, local color histograms. We show that this approach outperforms previous methods in cases of cluttered backgrounds, heterogenous objects, and occlusions. The proposed histograms can be used as statistical object descriptors within a template ma... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CAD Priors for Accurate and Flexible Instance Reconstruction

    Publication Year: 2017, Page(s):133 - 142
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (3156 KB) | HTML iconHTML

    We present an efficient and automatic approach for accurate instance reconstruction of big 3D objects from multiple, unorganized and unstructured point clouds, in presence of dynamic clutter and occlusions. In contrast to conventional scanning, where the background is assumed to be rather static, we aim at handling dynamic clutter where the background drastically changes during object scanning. Cu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Colored Point Cloud Registration Revisited

    Publication Year: 2017, Page(s):143 - 152
    Request permission for commercial reuse | Click to expandAbstract |PDF file iconPDF (4689 KB) | HTML iconHTML

    We present an algorithm for aligning two colored point clouds. The key idea is to optimize a joint photometric and geometric objective that locks the alignment along both the normal direction and the tangent plane. We extend a photometric objective for aligning RGB-D images to point clouds, by locally parameterizing the point cloud with a virtual camera. Experiments demonstrate that our algorithm ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.