4K4D：以4K解析度實時合成4D視圖

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

本文旨在實現動態3D場景的高保真度和實時視角合成，達到4K分辨率。最近，一些動態視角合成方法展現了令人印象深刻的渲染質量。然而，在渲染高分辨率圖像時，它們的速度仍然受限。為了克服這個問題，我們提出了4K4D，一種支持硬體光柵化並實現前所未有渲染速度的4D點雲表示法。我們的表示法建立在4D特徵網格上，使得點自然地被規範化並能夠穩健地進行優化。此外，我們設計了一種新型混合外觀模型，顯著提升了渲染質量同時保持效率。此外，我們開發了一種可微的深度剝離算法，有效地從RGB視頻中學習所提出的模型。實驗表明，我們的表示法在DNA-Rendering數據集上以1080p分辨率以每秒超過400幀的速度進行渲染，在ENeRF-Outdoor數據集上以4K分辨率以每秒80幀的速度進行渲染，使用RTX 4090 GPU，比以往方法快30倍，並實現了最先進的渲染質量。我們將釋出代碼以供重現。

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.