English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we develop a new method to automatically convert 2D linedrawings from three orthographic views into 3D CAD models. Existing methods forthis problem reconstruct 3D models by back-projecting the 2D observations into3D space while maintaining explicit correspondence between the input andoutput. Such methods are sensitive to errors and noises in the input, thusoften fail in practice where the input drawings created by human designers areimperfect. To overcome this difficulty, we leverage the attention mechanism ina Transformer-based sequence generation model to learn flexible mappingsbetween the input and output. Further, we design shape programs which aresuitable for generating the objects of interest to boost the reconstructionaccuracy and facilitate CAD modeling applications. Experiments on a newbenchmark dataset show that our method significantly outperforms existing oneswhen the inputs are noisy or incomplete.

PlankAssembly: Robust 3D Reconstruction from Three Orthographic Views with Learnt Shape Programs