Metasdf: Meta-learning signed distance functions

V Sitzmann, E Chan, R Tucker… - Advances in …, 2020 - proceedings.neurips.cc
Advances in Neural Information Processing Systems, 2020proceedings.neurips.cc
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 …
Abstract
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.
proceedings.neurips.cc
以上显示的是最相近的搜索结果。 查看全部搜索结果