Partial light field tomographic reconstruction from a fixed-camera focal stack
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.
Code (0)
등록된 구현이 없습니다.
Tasks
PositionSimilar Papers 제목 키워드 기반
Tomographic SAR Reconstruction for Forest Height Estimation
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 ObservationHigh-resolution tomographic reconstruction of optical absorbance through scattering media using neural fields
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 DrivingStabilizing Deep Tomographic Reconstruction
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 ReconstructionFrequency-regularized Neural Representation Method for Sparse-view Tomographic Reconstruction
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
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