Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration This paper proposes Analytic-Splatting, a method to improve anti-aliasing in 3D Gaussian Splatting (3DGS). 3DGS is a popular technique for 3D scene rendering, but it suffers from aliasing artifacts due to its discrete sampling approach. Analytic-Splatting addresses this issue by using an analytical approximation of the Gaussian integral within the 2D pixel window area. This approach allows for better capture of the intensity response of each pixel, resulting in improved anti-aliasing and detail fidelity. The key contribution of this paper is the derivation of an analytical solution to the problem of aliasing in 3DGS. This solution involves using a conditioned logistic function as an approximation of the cumulative distribution function (CDF) of a one-dimensional Gaussian signal. The Gaussian integral is then calculated by subtracting the CDFs. This analytical approximation is then applied to the two-dimensional pixel shading process, resulting in Analytic-Splatting. Analytic-Splatting is shown to be more effective than existing methods in reducing aliasing and preserving detail. The method is particularly effective in scenarios where the pixel footprint changes at different resolutions. The paper presents experiments on various datasets that demonstrate the effectiveness of Analytic-Splatting in achieving better anti-aliasing and detail fidelity compared to other methods.Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration This paper proposes Analytic-Splatting, a method to improve anti-aliasing in 3D Gaussian Splatting (3DGS). 3DGS is a popular technique for 3D scene rendering, but it suffers from aliasing artifacts due to its discrete sampling approach. Analytic-Splatting addresses this issue by using an analytical approximation of the Gaussian integral within the 2D pixel window area. This approach allows for better capture of the intensity response of each pixel, resulting in improved anti-aliasing and detail fidelity. The key contribution of this paper is the derivation of an analytical solution to the problem of aliasing in 3DGS. This solution involves using a conditioned logistic function as an approximation of the cumulative distribution function (CDF) of a one-dimensional Gaussian signal. The Gaussian integral is then calculated by subtracting the CDFs. This analytical approximation is then applied to the two-dimensional pixel shading process, resulting in Analytic-Splatting. Analytic-Splatting is shown to be more effective than existing methods in reducing aliasing and preserving detail. The method is particularly effective in scenarios where the pixel footprint changes at different resolutions. The paper presents experiments on various datasets that demonstrate the effectiveness of Analytic-Splatting in achieving better anti-aliasing and detail fidelity compared to other methods.