LGSDF: Continual Global Learning of Signed Distance Fields Aided by Local Updating

Implicit reconstruction of ESDF (Euclidean Signed Distance Field) involves training a neural network to regress the signed distance from any point to the nearest obstacle, which has the advantages of lightweight storage and continuous querying. However, existing algorithms usually rely on conflicting raw observations as training data, resulting in poor map performance. In this paper, we propose LGSDF, an ESDF continual Global learning algorithm aided by Local updating. In the front-end, anchors are uniformly distributed throughout the scene and incrementally updated based on preprocessed sensor observations, reducing estimation errors caused by limited viewing directions. In the back-end, a randomly initialized implicit ESDF neural network undergoes continuous self-supervised learning, driven by strategically sampled anchors, to produce smooth and continuous maps. Results from multiple scenes demonstrate that LGSDF outperforms SOTA ESDF mapping algorithm in constructing more accurate SDFs (SDF Error <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\downarrow$</tex-math></inline-formula> reduced by 37.12%) and meshes (Mesh Completion <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\downarrow$</tex-math></inline-formula> and Mesh Accuracy <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\downarrow$</tex-math></inline-formula> reduced by 23.88% and 10.76%, respectively). The project page of LGSDF is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://LGSDF.github.io/</uri>.