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

Neural Radiance Fields (NeRF) have shown remarkable performance in neuralrendering-based novel view synthesis. However, NeRF suffers from severe visualquality degradation when the input images have been captured under imperfectconditions, such as poor illumination, defocus blurring, and lens aberrations.Especially, defocus blur is quite common in the images when they are normallycaptured using cameras. Although few recent studies have proposed to rendersharp images of considerably high-quality, yet they still face many keychallenges. In particular, those methods have employed a Multi-Layer Perceptron(MLP) based NeRF, which requires tremendous computational time. To overcomethese shortcomings, this paper proposes a novel technique Sharp-NeRF -- agrid-based NeRF that renders clean and sharp images from the input blurryimages within half an hour of training. To do so, we used several grid-basedkernels to accurately model the sharpness/blurriness of the scene. Thesharpness level of the pixels is computed to learn the spatially varying blurkernels. We have conducted experiments on the benchmarks consisting of blurryimages and have evaluated full-reference and non-reference metrics. Thequalitative and quantitative results have revealed that our approach rendersthe sharp novel views with vivid colors and fine details, and it hasconsiderably faster training time than the previous works. Our project page isavailable at https://benhenryl.github.io/SharpNeRF/

Sharp-NeRF: Grid-based Fast Deblurring Neural Radiance Fields Using Sharpness Prior