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

Explicit feature-grid based NeRF models have shown promising results in termsof rendering quality and significant speed-up in training. However, thesemethods often require a significant amount of data to represent a single sceneor object. In this work, we present a compression model that aims to minimizethe entropy in the frequency domain in order to effectively reduce the datasize. First, we propose using the discrete cosine transform (DCT) on thetensorial radiance fields to compress the feature-grid. This feature-grid istransformed into coefficients, which are then quantized and entropy encoded,following a similar approach to the traditional video coding pipeline.Furthermore, to achieve a higher level of sparsity, we propose using an entropyparameterization technique for the frequency domain, specifically for DCTcoefficients of the feature-grid. Since the transformed coefficients areoptimized during the training phase, the proposed model does not require anyfine-tuning or additional information. Our model only requires a lightweightcompression pipeline for encoding and decoding, making it easier to applyvolumetric radiance field methods for real-world applications. Experimentalresults demonstrate that our proposed frequency domain entropy model canachieve superior compression performance across various datasets. The sourcecode will be made publicly available.

ECRF: Entropy-Constrained Neural Radiance Fields Compression with Frequency Domain Optimization