ACCURATE 3D RECONSTRUCTION FROM CIRCULAR LIGHT FIELD USING CNN-LSTM

A light field is formed by densely capturing images on a regular sub-aperture grid. Geometry information endowed in the epipolar plane images(EPI) can only lead to a 2.5D reconstruction. In order to obtain a full 360 view of an object, we focus on light fields captured by a circularly moving camera, resulting in circular light fields (or Cir-LFs in short). Compared with traditional EPIs, Circular EPIs(CEPIs) provide unique advantages, such as that corresponding points forming a 3D sinusoid like curve instead of a 2D straight line and geometry information encoded sequentially in multiple adjacent views along the curve. However, current reconstruction methods only focus on the 2D projection of 3D curve, leading to distortions in the reconstructed upper and lower surfaces. We propose to analyze 3D features contained in the 3D CEPI volume and we develop a deep CNN-LSTM network to model the gradient map in the CEPI volume. Additionally, a large scale Cir-LF dataset is constructed for research purpose. Experiments on both synthetic and real scenes demonstrate the effectiveness and generaliability of the proposed method.