Variational Light Field Analysis for Disparity Estimation and Super-Resolution

By Sven Wanner, Bastian Goldlücke. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014

597 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/fbaa16bdc7078a9b8558c71d67b3b1f6d90ea1d5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Soft 3D reconstruction for view synthesis (2017, result): “Since [Kalantari et al. 2016] compares favorably to [Zhang et al. 2016] and [Wanner and Goldluecke 2014] (using depth estimation of [Tao et al. 2013], [Wang et al. 2015] and [Jeon et al. 2015]) we refer to the reader to [Kalantari et al. 2016] for further comparisons with these methods.”
Light Field Image Processing: An Overview (2017, methodology): “To address the problem, Wanner and Goldluecke [66], [112] presented a con-”
Light field video capture using a learning-based hybrid imaging system (2017, unknown): “Wanner and Goldluecke (2014) propose an optimization approach to synthesize new angular views.”
Learning-based view synthesis for light field cameras (2016, methodology): “Existing view synthesis techniques [Chaurasia et al. 2011; Chaurasia et al. 2013; Wanner and Goldluecke 2014] have a specific way of combining these warped images and generating the final image.”
Light Field Super-Resolution with Zero-Shot Learning (2021, methodology): “Classic non-learning-based methods utilize projection and optimization techniques to super-resolve the reference view, relying on geometric [18, 30] and mathematical [4, 41] modeling of the 4D light field structure.”
Accurate depth map estimation from a lenslet light field camera (2015, background): “The additional light directions allow the image to be re-focused and the depth map of a scene to be estimated as demonstrated in [12, 17, 19, 23, 26, 29].”
Learning a Deep Convolutional Network for Light-Field Image Super-Resolution (2015, methodology): “Wanner and Goldluecke [29] additionally use an accurate depth map as a geometric guidance and perform angular SR.”
A Dataset and Evaluation Methodology for Depth Estimation on 4D Light Fields (2016, background): “The key difference to the classical multi-view scenario is the dense and regular sampling, which allows to develop novel and highly accurate methods for depth reconstruction [2,3,4,5,6], which can correctly take occlusions into account to recover fine details [7].”