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.
Users
Please
log in to take part in the discussion (add own reviews or comments).