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

3D-aware generative models have demonstrated their superb performance togenerate 3D neural radiance fields (NeRF) from a collection of monocular 2Dimages even for topology-varying object categories. However, these methodsstill lack the capability to separately control the shape and appearance of theobjects in the generated radiance fields. In this paper, we propose agenerative model for synthesizing radiance fields of topology-varying objectswith disentangled shape and appearance variations. Our method generatesdeformable radiance fields, which builds the dense correspondence between thedensity fields of the objects and encodes their appearances in a sharedtemplate field. Our disentanglement is achieved in an unsupervised mannerwithout introducing extra labels to previous 3D-aware GAN training. We alsodevelop an effective image inversion scheme for reconstructing the radiancefield of an object in a real monocular image and manipulating its shape andappearance. Experiments show that our method can successfully learn thegenerative model from unstructured monocular images and well disentangle theshape and appearance for objects (e.g., chairs) with large topologicalvariance. The model trained on synthetic data can faithfully reconstruct thereal object in a given single image and achieve high-quality texture and shapeediting results.

Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects