MetaSDF: Meta-learning Signed Distance Functions
This work addresses the need for efficient and accurate shape reconstruction from partial or noisy observations in computer graphics and vision, though it is incremental as it builds on existing neural implicit representation methods.
The paper tackles the problem of generalizing neural implicit shape representations across shapes by formalizing it as a meta-learning problem, resulting in test-time inference that is an order of magnitude faster than auto-decoder approaches while performing on par with them.
Neural implicit shape representations are an emerging paradigm that offers many potential benefits over conventional discrete representations, including memory efficiency at a high spatial resolution. Generalizing across shapes with such neural implicit representations amounts to learning priors over the respective function space and enables geometry reconstruction from partial or noisy observations. Existing generalization methods rely on conditioning a neural network on a low-dimensional latent code that is either regressed by an encoder or jointly optimized in the auto-decoder framework. Here, we formalize learning of a shape space as a meta-learning problem and leverage gradient-based meta-learning algorithms to solve this task. We demonstrate that this approach performs on par with auto-decoder based approaches while being an order of magnitude faster at test-time inference. We further demonstrate that the proposed gradient-based method outperforms encoder-decoder based methods that leverage pooling-based set encoders.