![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F14564763%2F7127122281456a6570e1d17e1eace58d%2Fdunhuang.png?generation=1770047891983328&alt=media)

 Dynamic 3D Gaussian Splatting (DyGS) enables real-time, high-fidelity rendering of dynamic scenes and is increasingly used in AR/VR/XR and volumetric video. However, naively storing a time-varying set of Gaussian primitives leads to prohibitive storage and bandwidth costs. While many compression approaches have been proposed, progress is slowed by the lack of a standardized benchmark that evaluates rate, rendering quality, and online decoding cost under a unified protocol.

DyGS-Bench focuses on a realistic deployment setting where only the reconstructed native Gaussian sequence is available (no original multi-view training images/videos). The goal of this Grand Challenge is to advance practical codecs that compress dynamic Gaussian assets into a compact bitstream and reconstruct renderable Gaussians efficiently.