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

Fully unsupervised 3D representation learning has gained attention owing toits advantages in data collection. A successful approach involves aviewpoint-aware approach that learns an image distribution based on generativemodels (e.g., generative adversarial networks (GANs)) while generating variousview images based on 3D-aware models (e.g., neural radiance fields (NeRFs)).However, they require images with various views for training, and consequently,their application to datasets with few or limited viewpoints remains achallenge. As a complementary approach, an aperture rendering GAN (AR-GAN) thatemploys a defocus cue was proposed. However, an AR-GAN is a CNN-based model andrepresents a defocus independently from a viewpoint change despite its highcorrelation, which is one of the reasons for its performance. As an alternativeto an AR-GAN, we propose an aperture rendering NeRF (AR-NeRF), which canutilize viewpoint and defocus cues in a unified manner by representing bothfactors in a common ray-tracing framework. Moreover, to learn defocus-aware anddefocus-independent representations in a disentangled manner, we proposeaperture randomized training, for which we learn to generate images whilerandomizing the aperture size and latent codes independently. During ourexperiments, we applied AR-NeRF to various natural image datasets, includingflower, bird, and face images, the results of which demonstrate the utility ofAR-NeRF for unsupervised learning of the depth and defocus effects.

AR-NeRF: Unsupervised Learning of Depth and Defocus Effects from Natural Images with Aperture Rendering Neural Radiance Fields