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 Non-Rigid Neural Radiance Fields (NR-NeRF), a reconstruction andnovel view synthesis approach for general non-rigid dynamic scenes. Ourapproach takes RGB images of a dynamic scene as input (e.g., from a monocularvideo recording), and creates a high-quality space-time geometry and appearancerepresentation. We show that a single handheld consumer-grade camera issufficient to synthesize sophisticated renderings of a dynamic scene from novelvirtual camera views, e.g. a `bullet-time' video effect. NR-NeRF disentanglesthe dynamic scene into a canonical volume and its deformation. Scenedeformation is implemented as ray bending, where straight rays are deformednon-rigidly. We also propose a novel rigidity network to better constrain rigidregions of the scene, leading to more stable results. The ray bending andrigidity network are trained without explicit supervision. Our formulationenables dense correspondence estimation across views and time, and compellingvideo editing applications such as motion exaggeration. Our code will be opensourced.

Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video