4K4D：实时4K分辨率下的4D视图合成

4K4D: Real-Time 4D View Synthesis at 4K Resolution

October 17, 2023

作者: Zhen Xu, Sida Peng, Haotong Lin, Guangzhao He, Jiaming Sun, Yujun Shen, Hujun Bao, Xiaowei Zhou

cs.AI

摘要

本文旨在实现动态3D场景在4K分辨率下的高保真实时视图合成。最近，一些动态视图合成方法展示了令人印象深刻的渲染质量。然而，在渲染高分辨率图像时，它们的速度仍然受限。为了克服这一问题，我们提出了4K4D，一种支持硬件光栅化并实现前所未有渲染速度的4D点云表示。我们的表示建立在4D特征网格上，使点自然正则化，并能够稳健地优化。此外，我们设计了一种新颖的混合外观模型，显著提升了渲染质量同时保持效率。此外，我们开发了一种可微的深度剥离算法，有效地从RGB视频中学习所提出的模型。实验表明，我们的表示可以在DNA-Rendering数据集的1080p分辨率上以超过400 FPS进行渲染，在ENeRF-Outdoor数据集的4K分辨率上以80 FPS在RTX 4090 GPU上进行渲染，比先前方法快30倍，并实现了最先进的渲染质量。我们将发布代码以便复现研究结果。

English

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. We will release the code for reproducibility.