English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For dense sampled light field (LF) reconstruction problem, existingapproaches focus on a depth-free framework to achieve non-Lambertianperformance. However, they trap in the trade-off "either aliasing or blurring"problem, i.e., pre-filtering the aliasing components (caused by the angularsparsity of the input LF) always leads to a blurry result. In this paper, weintend to solve this challenge by introducing an elaborately designed epipolarplane image (EPI) structure within a learning-based framework. Specifically, westart by analytically showing that decreasing the spatial scale of an EPI showshigher efficiency in addressing the aliasing problem than simply adoptingpre-filtering. Accordingly, we design a Laplacian Pyramid EPI (LapEPI)structure that contains both low spatial scale EPI (for aliasing) andhigh-frequency residuals (for blurring) to solve the trade-off problem. We thenpropose a novel network architecture for the LapEPI structure, termed asLapEPI-net. To ensure the non-Lambertian performance, we adopt atransfer-learning strategy by first pre-training the network with naturalimages then fine-tuning it with unstructured LFs. Extensive experimentsdemonstrate the high performance and robustness of the proposed approach fortackling the aliasing-or-blurring problem as well as the non-Lambertianreconstruction.

LapEPI-Net: A Laplacian Pyramid EPI structure for Learning-based Dense Light Field Reconstruction