A Latent Implicit 3D Shape Model for Multiple Levels of Detail
This addresses the limitation of existing implicit shape models for 3D rendering, which are either not smooth or limited to single objects, by providing a method that balances speed and accuracy for enhanced efficiency in implicit scene rendering.
The paper tackles the problem of implicit neural representations offering only a single level of detail by proposing a new shape modeling approach that enables multiple levels of detail while guaranteeing smooth surfaces at each level, achieving reconstruction quality on par with state-of-the-art models at finer levels.
Implicit neural representations map a shape-specific latent code and a 3D coordinate to its corresponding signed distance (SDF) value. However, this approach only offers a single level of detail. Emulating low levels of detail can be achieved with shallow networks, but the generated shapes are typically not smooth. Alternatively, some network designs offer multiple levels of detail, but are limited to overfitting a single object. To address this, we propose a new shape modeling approach, which enables multiple levels of detail and guarantees a smooth surface at each level. At the core, we introduce a novel latent conditioning for a multiscale and bandwith-limited neural architecture. This results in a deep parameterization of multiple shapes, where early layers quickly output approximated SDF values. This allows to balance speed and accuracy within a single network and enhance the efficiency of implicit scene rendering. We demonstrate that by limiting the bandwidth of the network, we can maintain smooth surfaces across all levels of detail. At finer levels, reconstruction quality is on par with the state of the art models, which are limited to a single level of detail.