Efficient 3D Object Segmentation from Densely Sampled Light Fields with Applications to 3D Reconstruction

From Kaan Yücer, Alexander Sorkine-Hornung, Oliver Wang, Olga Sorkine-Hornung:

Precise object segmentation in image data is a fundamental problem with various applications, including 3D object reconstruction. We present an efficient algorithm to automatically segment a static foreground object from highly cluttered background in light fields. A key insight and contribution of our paper is that a significant increase of the available input data can enable the design of novel, highly efficient approaches. In particular, the central idea of our method is to exploit high spatio-angular sampling on the order of thousands of input frames, e.g. captured as a hand-held video, such that new structures are revealed due to the increased coherence in the data. We first show how purely local gradient information contained in slices of such a dense light field can be combined with information about the camera trajectory to make efficient estimates of the foreground and background. These estimates are then propagated to textureless regions using edge-aware filtering in the epipolar volume. Finally, we enforce global consistency in a gathering step to derive a precise object segmentation both in 2D and 3D space, which captures fine geometric details even in very cluttered scenes. The design of each of these steps is motivated by efficiency and scalability, allowing us to handle large, real-world video datasets on a standard desktop computer... (paper)

Comments (0)

This post does not have any comments. Be the first to leave a comment below.


Post A Comment

You must be logged in before you can post a comment. Login now.

Featured Product

KINGSTAR Soft PLC - Replace Your PLC with an EtherCAT-enabled Soft PLC for Real-Time Motion Control and Machine Vision

KINGSTAR Soft PLC - Replace Your PLC with an EtherCAT-enabled Soft PLC for Real-Time Motion Control and Machine Vision

The top machine builders are switching from proprietary hardware-based PLCs, like Allen-Bradley, TwinCAT, Mitsubishi and KEYENCE, to open standards-based EtherCAT-enabled software PLCs on IPCs. KINGSTAR provides a fully-featured and integrated software PLC based on an open and accessible RTOS. KINGSTAR Soft PLC also includes add-on or third-party components for motion control and machine vision that are managed by a rich user interface for C++ programmers and non-developers alike.