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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Neural Radiance Fields (NeRF) have been widely adopted as practical andversatile representations for 3D scenes, facilitating various downstream tasks.However, different architectures, including plain Multi-Layer Perceptron (MLP),Tensors, low-rank Tensors, Hashtables, and their compositions, have theirtrade-offs. For instance, Hashtables-based representations allow for fasterrendering but lack clear geometric meaning, making spatial-relation-awareediting challenging. To address this limitation and maximize the potential ofeach architecture, we propose Progressive Volume Distillation with ActiveLearning (PVD-AL), a systematic distillation method that enables any-to-anyconversions between different architectures. PVD-AL decomposes each structureinto two parts and progressively performs distillation from shallower to deepervolume representation, leveraging effective information retrieved from therendering process. Additionally, a Three-Levels of active learning techniqueprovides continuous feedback during the distillation process, resulting inhigh-performance results. Empirical evidence is presented to validate ourmethod on multiple benchmark datasets. For example, PVD-AL can distill anMLP-based model from a Hashtables-based model at a 10~20X faster speed and0.8dB~2dB higher PSNR than training the NeRF model from scratch. Moreover,PVD-AL permits the fusion of diverse features among distinct structures,enabling models with multiple editing properties and providing a more efficientmodel to meet real-time requirements. Project website:http://sk-fun.fun/PVD-AL.

PVD-AL: Progressive Volume Distillation with Active Learning for Efficient Conversion Between Different NeRF Architectures