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

Implicit representations like Neural Radiance Fields (NeRF) showed impressiveresults for photorealistic rendering of complex scenes with fine details.However, ideal or near-perfectly specular reflecting objects such as mirrors,which are often encountered in various indoor scenes, impose ambiguities andinconsistencies in the representation of the reconstructed scene leading tosevere artifacts in the synthesized renderings. In this paper, we present anovel reflection tracing method tailored for the involved volume renderingwithin NeRF that takes these mirror-like objects into account while avoidingthe cost of straightforward but expensive extensions through standard pathtracing. By explicitly modeling the reflection behavior using physicallyplausible materials and estimating the reflected radiance with Monte-Carlomethods within the volume rendering formulation, we derive efficient strategiesfor importance sampling and the transmittance computation along rays from onlyfew samples. We show that our novel method enables the training of consistentrepresentations of such challenging scenes and achieves superior results incomparison to previous state-of-the-art approaches.

TraM-NeRF: Tracing Mirror and Near-Perfect Specular Reflections through Neural Radiance Fields