EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images
Light field cameras capture both the spatial and the angular properties of light rays in space. Due to its property, one can compute the depth from light fields in uncontrolled lighting environments, which is a big advantage over active sensing devices. Depth computed from light fields can be used for many applications including 3D modelling and refocusing. However, light field images from hand-held cameras have very narrow baselines with noise, making the depth estimation difficult. any approaches have been proposed to overcome these limitations for the light field depth estimation, but there is a clear trade-off between the accuracy and the speed in these methods. In this paper, we introduce a fast and accurate light field depth estimation method based on a fully-convolutional neural network. Our network is designed by considering the light field geometry and we also overcome the lack of training data by proposing light field specific data augmentation methods. We achieved the top rank in the HCI 4D Light Field Benchmark on most metrics, and we also demonstrate the effectiveness of the proposed method on real-world light-field images.
Code (2)
Tasks
Data AugmentationDepth EstimationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
3D Scene Reconstruction with Multi-layer Depth and Epipolar Transformers
We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilize…
3D Scene ReconstructionH-Net: Unsupervised Attention-based Stereo Depth Estimation Leveraging Epipolar Geometry
Depth estimation from a stereo image pair has become one of the most explored applications in computer vision, with most of the previous methods relying on fully supervised learning settings. However, due to the difficul…
Depth EstimationDepth PredictionStereo Depth EstimationStereo MatchingDualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium
Self-supervised multi-frame depth estimation achieves high accuracy by computing matching costs of pixel correspondences between adjacent frames, injecting geometric information into the network. These pixel-corresponden…
Depth EstimationDepth PredictionPose EstimationVisual Odometry Revisited: What Should Be Learnt?
In this work we present a monocular visual odometry (VO) algorithm which leverages geometry-based methods and deep learning. Most existing VO/SLAM systems with superior performance are based on geometry and have to be ca…
Deep LearningMonocular Visual OdometryVisual OdometryDELS-MVS: Deep Epipolar Line Search for Multi-View Stereo
We propose a novel approach for deep learning-based Multi-View Stereo (MVS). For each pixel in the reference image, our method leverages a deep architecture to search for the corresponding point in the source image direc…