paper-with-me

홈 › Papers

Partial light field tomographic reconstruction from a fixed-camera focal stack

2015-03-06 · A. Mousnier, E. Vural, C. Guillemot

This paper describes a novel approach to partially reconstruct high-resolution 4D light fields from a stack of differently focused photographs taken with a fixed camera. First, a focus map is calculated from this stack using a simple approach combining gradient detection and region expansion with graph-cut. Then, this focus map is converted into a depth map thanks to the calibration of the camera. We proceed after this with the tomographic reconstruction of the epipolar images by back-projecting the focused regions of the scene only. We call it masked back-projection. The angles of back-projection are calculated from the depth map. Thanks to the high angular resolution we achieve by suitably exploiting the image content captured over a large interval of focus distances, we are able to render puzzling perspective shifts although the original photographs were taken from a single fixed camera at a fixed position.

📄 PDF Abstract BibTeX arXiv:1503.01903

Code (0)

등록된 구현이 없습니다.

Tasks

Position

Similar Papers 제목 키워드 기반

Tomographic SAR Reconstruction for Forest Height Estimation

2024-12-01 · Grace Colverd, Jumpei Takami, Laura Schade, Karol Bot 외

Tree height estimation serves as an important proxy for biomass estimation in ecological and forestry applications. While traditional methods such as photogrammetry and Light Detection and Ranging (LiDAR) offer accurate …

Deep LearningEarth Observation

High-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields

2023-04-04 · Wuwei Ren, Siyuan Shen, Linlin Li, Shengyu Gao 외

Light scattering imposes a major obstacle for imaging objects seated deeply in turbid media, such as biological tissues and foggy air. Diffuse optical tomography (DOT) tackles scattering by volumetrically recovering the …

Autonomous Driving

Stabilizing Deep Tomographic Reconstruction

2020-08-04 · Weiwen Wu, Dianlin Hu, Wenxiang Cong, Hongming Shan 외

Tomographic image reconstruction with deep learning is an emerging field, but a recent landmark study reveals that several deep reconstruction networks are unstable for computed tomography (CT) and magnetic resonance ima…

Adversarial Attackcompressed sensingComputed Tomography (CT)Image Reconstruction

Frequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction

2024-09-22 · Jingmou Xian, Jian Zhu, Haolin Liao, Si Li

Sparse-view tomographic reconstruction is a pivotal direction for reducing radiation dose and augmenting clinical applicability. While many research works have proposed the reconstruction of tomographic images from spars…

Convolutional Dictionary Regularizers for Tomographic Inversion

2019-02-18

There has been a growing interest in the use of data-driven regularizers to solve inverse problems associated with computational imaging systems. The convolutional sparse representation model has recently gained attentio…

DenoisingDictionary Learning