Deep Medial Fields

Rebain, Daniel; Li, Ké; Sitzmann, Vincent; Yazdani, Soroosh; Yi, Kwang Moo; Tagliasacchi, Andrea

doi:10.48550/arxiv.2106.03804

Cited by 2 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods often lack topological constraints or exhibit large errors. Recently, deep learning has been used for skeleton construction including P2MAT-NET [Yang et al 2020], Deep medial fields [Rebain et al 2021], and Point2Skeleton [Lin et al 2021]. They do not guarantee accurate geometric features and suffer from generalization issues due to training data dependency.…”

Section: Medial Axis Simplificationmentioning

confidence: 99%

Polygrammar: Grammar for Digital Polymer Representation and Generation

et al. 2022

View full text Add to dashboard Cite

Polymers are widely studied materials with diverse properties and applications determined by molecular structures. It is essential to represent these structures clearly and explore the full space of achievable chemical designs. However, existing approaches cannot offer comprehensive design models for polymers because of their inherent scale and structural complexity. Here, a parametric, context-sensitive grammar designed specifically for polymers (PolyGrammar) is proposed. Using the symbolic hypergraph representation and 14 simple production rules, PolyGrammar can represent and generate all valid polyurethane structures. An algorithm is presented to translate any polyurethane structure from the popular Simplified Molecular-Input Line-entry System (SMILES) string format into the PolyGrammar representation. The representative power of PolyGrammar is tested by translating a dataset of over 600 polyurethane samples collected from the literature. Furthermore, it is shown that PolyGrammar can be easily extended to other copolymers and homopolymers. By offering a complete, explicit representation scheme and an explainable generative model with validity guarantees, PolyGrammar takes an essential step toward a more comprehensive and practical system for polymer discovery and exploration.As the first bridge between formal languages and chemistry, PolyGrammar also serves as a critical blueprint to inform the design of similar grammars for other chemistries, including organic and inorganic molecules.

show abstract

Section: Medial Axis Simplificationmentioning

confidence: 99%

Polygrammar: Grammar for Digital Polymer Representation and Generation

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Our approach leverages neural implicit representations to parameterize a continuous descriptor field which represents a manipulated object. Most saliently, such fields have been proposed to represent 3D geometry [5,25,27,29,33], appearance [22,24,34,37,38,44,47], and tactile properties [11]. They offer several benefits over conventional discrete representations: due to their continuous nature, they parameterize scene surfaces with "infinite resolution".…”

Section: B Neural Fields and Neural Scene Representationsmentioning

confidence: 99%