Visual aberrations are the imperfections in human vision, which play an important role in our everyday lives. Existing algorithms to simulate such conditions are either not suited for low-latency workloads or limit the kinds of supported aberrations. In this paper, we present a new simulation method that supports arbitrary visual aberrations and runs at interactive, near real-time performance on commodity hardware. Furthermore, our method only requires a single set of on-axis phase aberration coefficients as input and handles the dynamic change of pupil size and focus distance at runtime. We first describe a custom parametric eye model and parameter estimation method to find the physical properties of the simulated eye. Next, we talk about our parameter sampling strategy which we use with the estimated eye model to establish a coarse point-spread function (PSF) grid. We also propose a GPU-based interpolation scheme for the kernel grid which we use at runtime to obtain the final vision simulation by extending an existing tile-based convolution approach. We showcase the capabilities of our eye estimation and rendering processes using several different eye conditions and provide the corresponding performance metrics to demonstrate the applicability of our method for interactive environments.

中文翻译：

---

使用 Tiled Point-Spread Function Splatting 有效渲染眼波前像差

视觉像差是人类视觉中的缺陷，在我们的日常生活中扮演着重要的角色。用于模拟此类条件的现有算法要么不适合低延迟工作负载，要么限制了支持的畸变类型。在本文中，我们提出了一种新的模拟方法，该方法支持任意视觉像差，并在商品硬件上以交互式、近实时的性能运行。此外，我们的方法只需要一组轴上相位像差系数作为输入，并在运行时处理瞳孔大小和焦距的动态变化。我们首先描述了一个自定义参数眼模型和参数估计方法，以找到模拟眼的物理特性。下一个，我们讨论了我们的参数采样策略，我们将其与估计的眼模型一起使用来建立粗点扩展函数 (PSF) 网格。我们还为内核网格提出了一种基于 GPU 的插值方案，我们在运行时使用该方案通过扩展现有的基于图块的卷积方法来获得最终的视觉模拟。我们使用几种不同的眼睛条件展示了我们的眼睛估计和渲染过程的能力，并提供了相应的性能指标来证明我们的方法在交互式环境中的适用性。