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

In this paper, we present Consistent4D, a novel approach for generating 4Ddynamic objects from uncalibrated monocular videos. Uniquely, we cast the360-degree dynamic object reconstruction as a 4D generation problem,eliminating the need for tedious multi-view data collection and cameracalibration. This is achieved by leveraging the object-level 3D-aware imagediffusion model as the primary supervision signal for training Dynamic NeuralRadiance Fields (DyNeRF). Specifically, we propose a Cascade DyNeRF tofacilitate stable convergence and temporal continuity under the supervisionsignal which is discrete along the time axis. To achieve spatial and temporalconsistency, we further introduce an Interpolation-driven Consistency Loss. Itis optimized by minimizing the discrepancy between rendered frames from DyNeRFand interpolated frames from a pre-trained video interpolation model. Extensiveexperiments show that our Consistent4D can perform competitively to prior artalternatives, opening up new possibilities for 4D dynamic object generationfrom monocular videos, whilst also demonstrating advantage for conventionaltext-to-3D generation tasks. Our project page ishttps://consistent4d.github.io/.

Consistent4D: Consistent 360{\deg} Dynamic Object Generation from Monocular Video