Neural Transmitted Radiance Fields

Chengxuan Zhu, Renjie Wan, Boxin Shi*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

7 Citations (Scopus)


Neural radiance fields (NeRF) have brought tremendous progress to novel view synthesis. Though NeRF enables the rendering of subtle details in a scene by learning from a dense set of images, it also reconstructs the undesired reflections when we capture images through glass. As a commonly observed interference, the reflection would undermine the visibility of the desired transmitted scene behind glass by occluding the transmitted light rays. In this paper, we aim at addressing the problem of rendering novel transmitted views given a set of reflection-corrupted images. By introducing the transmission encoder and recurring edge constraints as guidance, our neural transmitted radiance fields can resist such reflection interference during rendering and reconstruct high-fidelity results even under sparse views. The proposed method achieves superior performance from the experiments on a newly collected dataset compared with state-of-the-art methods. Our code and data is available at
Original languageEnglish
Title of host publication36th Conference on Neural Information Processing Systems (NeurIPS 2022)
PublisherNeural Information Processing Systems Foundation
Number of pages13
Publication statusPublished - 29 Nov 2022
Event36th Conference on Neural Information Processing Systems, NeurIPS 2022 - New Orleans Convention Center, New Orleans, United States
Duration: 28 Nov 20229 Dec 2022

Publication series

NameAdvances in Neural Information Processing Systems
ISSN (Print)1049-5258
NameNeurIPS Proceedings


Conference36th Conference on Neural Information Processing Systems, NeurIPS 2022
Country/TerritoryUnited States
CityNew Orleans
Internet address


Dive into the research topics of 'Neural Transmitted Radiance Fields'. Together they form a unique fingerprint.

Cite this