4D-Rotor Gaussian Splatting：迈向动态场景的高效新视角合成
4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenes
AI总结：
提出4DRotorGS，用各向异性4D XYZT高斯与时间切片表示动态场景，并以CUDA实现实时渲染，在多样运动场景中优于现有方法。
摘要：
我们研究动态场景的新视角合成（NVS）问题。近期的神经方法已在静态3D场景上取得出色的NVS结果，但将其扩展到4D时变场景仍非易事。以往工作通常通过学习一个规范空间以及隐式或显式形变场来编码动态，这在突发运动或生成高保真渲染等具有挑战性的场景中会遇到困难。本文提出4D Gaussian Splatting（4DRotorGS），这是一种受3D Gaussian Splatting在静态场景中的成功启发、用各向异性4D XYZT高斯表示动态场景的新方法。我们通过对4D高斯进行时间切片来建模每个时间戳的动态，这些高斯自然构成动态3D高斯，并可无缝投影到图像中。作为一种显式时空表示，4DRotorGS在建模复杂动态和精细细节方面表现出强大能力，尤其适用于具有突变运动的场景。我们进一步在高度优化的CUDA加速框架中实现时间切片和splatting技术，在RTX 3090 GPU上实现高达277 FPS、在RTX 4090 GPU上实现583 FPS的实时推理渲染速度。对具有多样运动的场景进行的严格评估展示了4DRotorGS卓越的效率和效果，其在定量和定性上均持续优于现有方法。
英文摘要：
We consider the problem of novel-view synthesis (NVS) for dynamic scenes. Recent neural approaches have accomplished exceptional NVS results for static 3D scenes, but extensions to 4D time-varying scenes remain non-trivial. Prior efforts often encode dynamics by learning a canonical space plus implicit or explicit deformation fields, which struggle in challenging scenarios like sudden movements or generating high-fidelity renderings. In this paper, we introduce 4D Gaussian Splatting (4DRotorGS), a novel method that represents dynamic scenes with anisotropic 4D XYZT Gaussians, inspired by the success of 3D Gaussian Splatting in static scenes. We model dynamics at each timestamp by temporally slicing the 4D Gaussians, which naturally compose dynamic 3D Gaussians and can be seamlessly projected into images. As an explicit spatial-temporal representation, 4DRotorGS demonstrates powerful capabilities for modeling complicated dynamics and fine details--especially for scenes with abrupt motions. We further implement our temporal slicing and splatting techniques in a highly optimized CUDA acceleration framework, achieving real-time inference rendering speeds of up to 277 FPS on an RTX 3090 GPU and 583 FPS on an RTX 4090 GPU. Rigorous evaluations on scenes with diverse motions showcase the superior efficiency and effectiveness of 4DRotorGS, which consistently outperforms existing methods both quantitatively and qualitatively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
