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 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, mostexisting approaches rely on 3D supervision, annotation of 2D images withkeypoints or poses, and/or training with multiple views of each objectinstance. Our framework is very general: it can be trained in similar settingsto existing approaches, while also supporting weaker supervision. Importantly,it can be trained purely from 2D images, without pose annotations, and withonly a single view per instance. We employ meshes as an output representation,instead of voxels used in most prior work. This allows us to reason overlighting parameters and exploit shading information during training, whichprevious 2D-supervised methods cannot. Thus, our method can learn to generateand reconstruct concave object classes. We evaluate our approach in varioussettings, showing that: (i) it learns to disentangle shape from pose andlighting; (ii) using shading in the loss improves performance compared to justsilhouettes; (iii) when using a standard single white light, our modeloutperforms state-of-the-art 2D-supervised methods, both with and without posesupervision, thanks to exploiting shading cues; (iv) performance improvesfurther when using multiple coloured lights, even approaching that ofstate-of-the-art 3D-supervised methods; (v) shapes produced by our modelcapture smooth surfaces and fine details better than voxel-based approaches;and (vi) our approach supports concave classes such as bathtubs and sofas,which methods based on silhouettes cannot learn.

Learning single-image 3D reconstruction by generative modelling of shape, pose and shading