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

We present a new weakly supervised learning-based method for generating novelcategory-specific 3D shapes from unoccluded image collections. Our method isweakly supervised and only requires silhouette annotations from unoccluded,category-specific objects. Our method does not require access to the object's3D shape, multiple observations per object from different views, intra-imagepixel-correspondences, or any view annotations. Key to our method is a novelmulti-projection generative adversarial network (MP-GAN) that trains a 3D shapegenerator to be consistent with multiple 2D projections of the 3D shapes, andwithout direct access to these 3D shapes. This is achieved through multiplediscriminators that encode the distribution of 2D projections of the 3D shapesseen from a different views. Additionally, to determine the view informationfor each silhouette image, we also train a view prediction network onvisualizations of 3D shapes synthesized by the generator. We iterativelyalternate between training the generator and training the view predictionnetwork. We validate our multi-projection GAN on both synthetic and real imagedatasets. Furthermore, we also show that multi-projection GANs can aid inlearning other high-dimensional distributions from lower dimensional trainingdatasets, such as material-class specific spatially varying reflectanceproperties from images.

Synthesizing 3D Shapes from Silhouette Image Collections using Multi-projection Generative Adversarial Networks