Enhanced reconstruction of three-dimensional shape and texture from integral photography images

Abstract

A method for the reconstruction of 3D shape and texture from integral photography (IP) images is presented. Sharing the same principles with stereoscopic-based object reconstruction, it offers increased robustness to noise and occlusions due to the unique characteristics of IP images. A coarse-to-fine approach is used, employing what we believe to be a novel grid refinement step in order to increase the quality of the reconstructed objects. The proposed method's properties include configurable depth accuracy and direct and seamless triangulation. We evaluate our method using synthetic data from a computer-simulated IP setup as well as real data from a simple yet effective digital IP setup. Experiments show reconstructed objects of high-quality indicating that IP can be a competitive modality for 3D object reconstruction.

Surface reconstruction from multiview projection data employing a microlens array-based optical detector: a simulation study

“…[17][18][19] Shape reconstruction or depth retrieval using MLAs can be performed from a single projection by finding corresponding points among neighboring EIs or adjacent focal point images. 15,20 Due to the limited number of microlenses and/or light trajectories, the reconstructed surface possesses a rather low-depth resolution and is insufficient for the downstream task of image reconstruction from optical data (tomography).…”

Near Real-Time 3D Reconstruction from InIm Video Stream

“…A method that is focused on the reconstruction of a fully 3D surface model is proposed in [12], where 3D shape and texture of real-life objects are reconstructed using the InIm technique. The method extends the classic stereo correspondence problem using horizontal and vertical parallax and multiple correspondences.…”

“…In this paper, an architecture is proposed for efficiently enhancing the performance of a 3D reconstruction method, such as the one presented in [12]. The proposed hardware illustrates a significant speed improvement over the software method, by parallelizing time-consuming and repetitive processing tasks that form the inner loop of the reconstruction algorithm and favor hardware implementation.…”

“…The rest of the paper is divided into 4 sections. In section 2, the 3D reconstruction method [12] is outlined. In section 3, we describe the hardware system and present its main design considerations.…”

“…The method proposed in [12], estimates the 3D shape and texture of an object from a single Integral Image. To this end a two step process is applied: first, 3D points (vertices) on the surface of the object are computed and second, these points are connected in a polygonal (e.g.…”