Towards Efficient Local 3D Conditioning
Name
3610542.3626151.pdf
Size
5.06 MB
Format
Adobe PDF
Checksum (MD5)
aa9725a6c414096bf0a41ad5a97050eb
Author(s)
Zhang, Dingxi
Lukoianov, Artem
Date Issued
November 28, 2023
Publisher
ACM|SIGGRAPH Asia 2023 Posters
Citation
Zhang, Dingxi and Lukoianov, Artem. 2023. "Towards Efficient Local 3D Conditioning."
Version
Final published version
Abstract
Recently, Neural Implicit Representations (NIRs) have gained popularity for learning-based 3D shape representation. General representations, i.e. ones that share a decoder across a family of geometries have multiple advantages such as ability of generating previously unseen samples and smoothly interpolating between training examples. These representations, however, impose a trade-off between quality of reconstruction and memory footprint stored per sample. Globally conditioned NIRs suffer from a lack of quality in capturing intricate shape details, while densely conditioned NIRs demand excessive memory resources. In this work we suggest using a Neural Network to approximate a grid of latent codes, while sharing the decoder across the entire category. Our model achieves a significantly better reconstruction quality compared to globally conditioned methods, while using less memory per sample to store single geometry.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3610542.3626151
