RadSplat：基于辐射场信息的高斯飞溅，用于具有900+ FPS的稳健实时渲染

摘要

最近在视图合成和实时渲染方面取得了重大进展，以令人印象深刻的渲染速度实现了逼真的质量。尽管基于辐射场的方法在具有挑战性的场景（如野外捕捉和大规模场景）中实现了最先进的质量，但往往受到与体积渲染相关的过高计算需求的困扰。另一方面，基于高斯飞溅的方法依赖光栅化，自然实现了实时渲染，但在更具挑战性的场景中表现不佳，因为其脆弱的优化启发式方法。在这项工作中，我们提出了RadSplat，这是一种用于复杂场景稳健实时渲染的轻量级方法。我们的主要贡献有三个方面。首先，我们将辐射场用作优化基于点的场景表示的先验和监督信号，从而提高质量并实现更稳健的优化。接下来，我们开发了一种新颖的修剪技术，减少整体点数同时保持高质量，从而实现更小更紧凑的场景表示，并具有更快的推理速度。最后，我们提出了一种新颖的测试时滤波方法，进一步加速渲染并实现扩展到更大的房屋大小场景。我们发现，我们的方法使得复杂捕捉以900+ FPS的速度实现了最先进的合成。

English

Recent advances in view synthesis and real-time rendering have achieved photorealistic quality at impressive rendering speeds. While Radiance Field-based methods achieve state-of-the-art quality in challenging scenarios such as in-the-wild captures and large-scale scenes, they often suffer from excessively high compute requirements linked to volumetric rendering. Gaussian Splatting-based methods, on the other hand, rely on rasterization and naturally achieve real-time rendering but suffer from brittle optimization heuristics that underperform on more challenging scenes. In this work, we present RadSplat, a lightweight method for robust real-time rendering of complex scenes. Our main contributions are threefold. First, we use radiance fields as a prior and supervision signal for optimizing point-based scene representations, leading to improved quality and more robust optimization. Next, we develop a novel pruning technique reducing the overall point count while maintaining high quality, leading to smaller and more compact scene representations with faster inference speeds. Finally, we propose a novel test-time filtering approach that further accelerates rendering and allows to scale to larger, house-sized scenes. We find that our method enables state-of-the-art synthesis of complex captures at 900+ FPS.

RadSplat：基于辐射场信息的高斯飞溅，用于具有900+ FPS的稳健实时渲染

RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS

摘要

Summary

Support

Support