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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present a unified framework tackling two problems: class-specific 3Dreconstruction from a single image, and generation of new 3D shape samples.These tasks have received considerable attention recently; however, existingapproaches rely on 3D supervision, annotation of 2D images with keypoints orposes, and/or training with multiple views of each object instance. Ourframework is very general: it can be trained in similar settings to theseexisting approaches, while also supporting weaker supervision scenarios.Importantly, it can be trained purely from 2D images, without ground-truth poseannotations, and with a single view per instance. We employ meshes as an outputrepresentation, instead of voxels used in most prior work. This allows us toexploit shading information during training, which previous 2D-supervisedmethods cannot. Thus, our method can learn to generate and reconstruct concaveobject classes. We evaluate our approach on synthetic data in various settings,showing that (i) it learns to disentangle shape from pose; (ii) using shadingin the loss improves performance; (iii) our model is comparable or superior tostate-of-the-art voxel-based approaches on quantitative metrics, whileproducing results that are visually more pleasing; (iv) it still performs wellwhen given supervision weaker than in prior works.

Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision