Neighbor-Aware View Synthesis for Restoring Missing Views in Light-Field Camera Arrays
2026-08-24 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving light-field cameras when some cameras in the array stop working and cause missing images. They create a new method that uses nearby working cameras and their positions to help a special AI model called a conditional GAN fill in the missing views. Their system makes realistic and clear images that match the original scenes better than previous methods. Tests on both fake and real light-field data show their approach works well for fixing broken or missing camera views.
Light-field imagingCamera arrayView synthesisGenerative Adversarial NetworkConditional GANView interpolationPositional encodingImage reconstructionDepth estimationFault-tolerant imaging
Authors
Sakshi Goel, Ayush Goyal, K S Venkatesh, Koteswar Rao Jerripothula
Abstract
In light-field (LF) imaging systems, dense spatial sampling from a camera array enables powerful post-capture capabilities such as refocusing and depth estimation. However, real-world LF capture is often affected by hardware malfunctions, where one or more cameras in the array fail, leading to missing sub-aperture images and degraded reconstruction quality. This paper addresses the problem of defective or missing view restoration in light-field camera arrays. We propose a novel generative framework that synthesizes the absent views by exploiting information from a carefully selected subset of neighboring cameras. These selected images, along with a positional encoding map indicating both their locations and the desired target view, are fed into a conditional Generative Adversarial Network (cGAN) trained to generate the missing viewpoint in a geometrically consistent manner. Extensive experiments on synthetic and real-world LF datasets demonstrate that our method produces visually plausible and photometrically accurate reconstructions, outperforming baselines for view interpolation both quantitatively and qualitatively. The proposed framework thus offers a robust and efficient solution for fault-tolerant light-field image acquisition.