Style4D-Bench: A Benchmark Suite for 4D Stylization

TL;DR

Style4D-Bench is a comprehensive benchmark suite for 4D stylization that standardizes evaluation, and the Style4D framework achieves state-of-the-art results in dynamic 3D scene stylization.

Contribution

The paper introduces Style4D-Bench, the first benchmark suite for 4D stylization, and presents Style4D, a novel framework leveraging 4D Gaussian Splatting for improved stylized rendering.

Findings

Style4D outperforms existing methods in 4D stylization.

The benchmark enables standardized evaluation of 4D stylization methods.

Style4D achieves high-quality, temporally coherent stylized 3D scenes.

Abstract

We introduce Style4D-Bench, the first benchmark suite specifically designed for 4D stylization, with the goal of standardizing evaluation and facilitating progress in this emerging area. Style4D-Bench comprises: 1) a comprehensive evaluation protocol measuring spatial fidelity, temporal coherence, and multi-view consistency through both perceptual and quantitative metrics, 2) a strong baseline that make an initial attempt for 4D stylization, and 3) a curated collection of high-resolution dynamic 4D scenes with diverse motions and complex backgrounds. To establish a strong baseline, we present Style4D, a novel framework built upon 4D Gaussian Splatting. It consists of three key components: a basic 4DGS scene representation to capture reliable geometry, a Style Gaussian Representation that leverages lightweight per-Gaussian MLPs for temporally and spatially aware appearance control, and a Holistic Geometry-Preserved Style Transfer module designed to enhance spatio-temporal consistency via contrastive coherence learning and structural content preservation. Extensive experiments on Style4D-Bench demonstrate that Style4D achieves state-of-the-art performance in 4D stylization, producing fine-grained stylistic details with stable temporal dynamics and consistent multi-view rendering. We expect Style4D-Bench to become a valuable resource for benchmarking and advancing research in stylized rendering of dynamic 3D scenes. Project page: https://becky-catherine.github.io/Style4D . Code: https://github.com/Becky-catherine/Style4D-Bench .