%0 Journal Article %1 RAL2022_2 %A Yuan, Y. %A Nüchter, A. %D 2022 %J IEEE Robotics and Automation Letters (RAL) %K imported myown %N 3 %P 7763--7770 %R 10.1109/LRA.2022.3185383 %T An Algorithm for the SE(3)-Transformation on Neural Implicit Maps for Remapping Functions %U https://robotik.informatik.uni-wuerzburg.de/telematics/download/ral2022_2.pdf %V 7 %X Implicit representations are widely used for object reconstruction due their efficiency and flexibility. In 2021, a novel structure named neural implicit map has been invented for incremental reconstruction. A neural implicit map alleviates the problem of inefficient memory cost of previous online 3D dense reconstruction while producing better quality. However, the neural implicit map suffers the limitations that it does not support remapping as the frames of scans are encoded into a deep prior after generating the neural implicit map. This means, neither this generation process is invertible, nor a deep prior is transformable. The non-remappable property makes it not possible to apply loop-closure techniques. We present an implicit-map based transformation algorithm to fill this gap. As our implicit-map is transformable, our model supports remapping for this special map of latent features. Experiments show that our remapping module is capable to well-transform neural implicit maps to new poses. Embedded into a SLAM framework, our mapping model is able to tackle remapping of loop-closures and demonstrates high-quality surface reconstruction. Our implementation is available at github (https://github.com/Jarrome/IMT_Mapping) for the research community.

@article{RAL2022_2, abstract = {Implicit representations are widely used for object reconstruction due their efficiency and flexibility. In 2021, a novel structure named neural implicit map has been invented for incremental reconstruction. A neural implicit map alleviates the problem of inefficient memory cost of previous online 3D dense reconstruction while producing better quality. However, the neural implicit map suffers the limitations that it does not support remapping as the frames of scans are encoded into a deep prior after generating the neural implicit map. This means, neither this generation process is invertible, nor a deep prior is transformable. The non-remappable property makes it not possible to apply loop-closure techniques. We present an implicit-map based transformation algorithm to fill this gap. As our implicit-map is transformable, our model supports remapping for this special map of latent features. Experiments show that our remapping module is capable to well-transform neural implicit maps to new poses. Embedded into a SLAM framework, our mapping model is able to tackle remapping of loop-closures and demonstrates high-quality surface reconstruction. Our implementation is available at github (https://github.com/Jarrome/IMT_Mapping) for the research community.}, added-at = {2022-06-30T17:10:42.000+0200}, author = {Yuan, Y. and N{\"u}chter, A.}, biburl = {https://www.bibsonomy.org/bibtex/2f108d3ec35677539db9949bad235c127/nuechter76}, doi = {10.1109/LRA.2022.3185383}, interhash = {20d6462ba04cc5944c3bc25b23cb74d0}, intrahash = {f108d3ec35677539db9949bad235c127}, journal = {IEEE Robotics and Automation Letters (RAL)}, keywords = {imported myown}, month = {July}, number = 3, pages = {7763--7770}, timestamp = {2022-07-03T11:27:00.000+0200}, title = {{An Algorithm for the SE(3)-Transformation on Neural Implicit Maps for Remapping Functions}}, url = {https://robotik.informatik.uni-wuerzburg.de/telematics/download/ral2022_2.pdf}, volume = 7, year = 2022 }