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

Data-driven generative modeling has made remarkable progress by leveragingthe power of deep neural networks. A reoccurring challenge is how to enable amodel to generate a rich variety of samples from the entire targetdistribution, rather than only from a distribution confined to the trainingdata. In other words, we would like the generative model to go beyond theobserved samples and learn to generate ``unseen'', yet still plausible, data.In our work, we present CompoNet, a generative neural network for 2D or 3Dshapes that is based on a part-based prior, where the key idea is for thenetwork to synthesize shapes by varying both the shape parts and theircompositions. Treating a shape not as an unstructured whole, but as a(re-)composable set of deformable parts, adds a combinatorial dimension to thegenerative process to enrich the diversity of the output, encouraging thegenerator to venture more into the ``unseen''. We show that our part-basedmodel generates richer variety of plausible shapes compared with baselinegenerative models. To this end, we introduce two quantitative metrics toevaluate the diversity of a generative model and assess how well the generateddata covers both the training data and unseen data from the same targetdistribution. Code is available at https://github.com/nschor/CompoNet.

CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition