arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12949cs.GR
收藏

基于神经辐射场的实时渲染

Real-time Rendering with a Neural Irradiance Volume

Huawei Technologies(华为技术);Graz University of Technology(格拉茨工业大学)

Arno Coomans, Giacomo Nazzaro, Edoardo A. Dominici, Christian Döring, Floor Verhoeven, Konstantinos Vardis, Markus Steinberger

AI总结:

本文提出神经辐照度体积(NIV)技术,通过紧凑模型实现高精度实时 diffuse 全局光照渲染,提升质量并降低内存消耗。

摘要:

在实时渲染中, diffuse 全局光照通常通过预先计算并存储在 3D 探针网格中的辐照度来近似。只要场景的大部分内容保持静止,探针可以为所有浸入辐照度体积中的表面近似辐照度,包括新的动态物体。然而,这种方法却存在混叠伪影和高内存消耗的问题。我们提出了神经辐照度体积(NIV),一种基于神经网络的技术,通过一个紧凑的预计算模型实现精确的实时 diffuse 全局光照渲染,克服了传统探针方法的限制,如昂贵的内存足迹、混叠伪影和场景特定的启发式方法。关键的洞察是神经压缩创建了适应性和 amortized 的辐照度表示,绕过了基于网格的方法的立方扩展。我们的优越内存扩展提高了质量,同一内存预算下至少提高 10 倍,并允许对更高维的辐照度场进行简单的表示,允许在不需要运行时额外计算的情况下渲染时间变化或动态效果。与其他神经渲染技术不同,我们的方法在严格的实时约束下工作,提供快速推理(在全高清分辨率下,消费者 GPU 上每帧约 1 毫秒),减少内存使用(中等大小场景 1-5 MB),并且只需要 G-buffer 作为输入,而无需昂贵的光线追踪或去噪。

英文摘要:

Rendering diffuse global illumination in real-time is often approximated by pre-computing and storing irradiance in a 3D grid of probes. As long as most of the scene remains static, probes approximate irradiance for all surfaces immersed in the irradiance volume, including novel dynamic objects. This approach, however, suffers from aliasing artifacts and high memory consumption. We propose Neural Irradiance Volume (NIV), a neural-based technique that allows accurate real-time rendering of diffuse global illumination via a compact pre-computed model, overcoming the limitations of traditional probe-based methods, such as the expensive memory footprint, aliasing artifacts, and scene-specific heuristics. The key insight is that neural compression creates an adaptive and amortized representation of irradiance, circumventing the cubic scaling of grid-based methods. Our superior memory-scaling improves quality by at least 10x at the same memory budget, and enables a straightforward representation of higher-dimensional irradiance fields, allowing rendering of time-varying or dynamic effects without requiring additional computation at runtime. Unlike other neural rendering techniques, our method works within strict real-time constraints, providing fast inference (around 1 ms per frame on consumer GPUs at full HD resolution), reduced memory usage (1-5 MB for medium-sized scenes), and only requires a G-buffer as input, without expensive ray tracing or denoising.

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。

↑