ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression

Guangchi Fang, Qingyong Hu, Longguang Wang, Yulan Guo

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: NeRF; NeRF Compression; 3D Data Compression

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: In this work, we study the problem of explicit NeRF compression. Through analyzing recent explicit NeRF models, we reformulate the task of explicit NeRF compression as 3D data compression. We further introduce our NeRF compression framework, Attributed Compression of Radiance Field (ACRF), which focuses on the compression of the explicit neural 3D representation. The neural 3D structure is pruned and converted to points with features, which are further encoded using importance-guided feature encoding. Furthermore, we employ an importance-prioritized entropy model to estimate the probability distribution of transform coefficients, which are then entropy coded with an arithmetic coder using the predicted distribution. Within this framework, we present two models, ACRF and ACRF-F, to strike a balance between compression performance and encoding time budget. Our experiments, which include both synthetic and real-world datasets such as Synthetic-NeRF and Tanks&Temples, demonstrate the superior performance of our proposed algorithm.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: general machine learning (i.e., none of the above)

Submission Number: 2447