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

Modeling dynamic, large-scale urban scenes is challenging due to their highlyintricate geometric structures and unconstrained dynamics in both space andtime. Prior methods often employ high-level architectural priors, separatingstatic and dynamic elements, resulting in suboptimal capture of theirsynergistic interactions. To address this challenge, we present a unifiedrepresentation model, called Periodic Vibration Gaussian (PVG). PVG builds uponthe efficient 3D Gaussian splatting technique, originally designed for staticscene representation, by introducing periodic vibration-based temporaldynamics. This innovation enables PVG to elegantly and uniformly represent thecharacteristics of various objects and elements in dynamic urban scenes. Toenhance temporally coherent representation learning with sparse training data,we introduce a novel flow-based temporal smoothing mechanism and aposition-aware adaptive control strategy. Extensive experiments on Waymo OpenDataset and KITTI benchmarks demonstrate that PVG surpasses state-of-the-artalternatives in both reconstruction and novel view synthesis for both dynamicand static scenes. Notably, PVG achieves this without relying on manuallylabeled object bounding boxes or expensive optical flow estimation. Moreover,PVG exhibits 50/6000-fold acceleration in training/rendering over the bestalternative.

Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering