This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recently, some methods on dynamic view synthesis have shown impressive rendering quality. However, their speed is still limited when rendering high-resolution images. To overcome this problem, we propose 4K4D, a 4D point cloud representation that supports hardware rasterization and enables unprecedented rendering speed. Our representation is built on a 4D feature grid so that the points are naturally regularized and can be robustly optimized. In addition, we design a novel hybrid appearance model that significantly boosts the rendering quality while preserving efficiency. Moreover, we develop a differentiable depth peeling algorithm to effectively learn the proposed model from RGB videos. Experiments show that our representation can be rendered at over 400 FPS on the DNA-Rendering dataset at 1080p resolution and 80 FPS on the ENeRF-Outdoor dataset at 4K resolution using an RTX 4090 GPU, which is 30x faster than previous methods and achieves the state-of-the-art rendering quality. Our project page is available at https://zju3dv.github.io/4k4d/.

翻译：本文旨在实现4K分辨率下动态三维场景的高保真实时视图合成。近年来，部分动态视图合成方法已展现出令人印象深刻的渲染质量，但在渲染高分辨率图像时速度仍受局限。为解决此问题，我们提出4K4D——一种支持硬件光栅化且能实现前所未有渲染速度的四维点云表示。该表示基于四维特征网格构建，使点云天然具备正则化特性并可被稳健优化。此外，我们设计了一种新型混合外观模型，在保持效率的同时显著提升渲染质量。进一步地，我们开发了可微分深度剥离算法，以从RGB视频中有效学习所提模型。实验表明，在RTX 4090 GPU上，我们的表示方法在DNA-Rendering数据集的1080p分辨率下可实现超过400 FPS的渲染速度，在ENeRF-Outdoor数据集的4K分辨率下可达80 FPS，相比先前方法提速30倍，并实现了最先进的渲染质量。项目页面访问地址：https://zju3dv.github.io/4k4d/。