ConeGaussian: Anti-Aliased Gaussian Ray-Tracing for Generic Central Cameras

• URL: http://arxiv.org/abs/2609.13397v1
• Date: Fri, 11 Sep 2026 18:05:07 GMT
• Title: ConeGaussian: Anti-Aliased Gaussian Ray-Tracing for Generic Central Cameras
• Abstract summary: We present ConeGaussian, a camera-model-agnostic anti-aliasing framework for Gaussian ray-based rendering.<n>We derive a closed-form response under a locally linear, depth-local, moment-matched approximation of the finite pixel footprint.<n>Unlike in mip-splatting, our scene-space frequency floor and filtering enable trivial composition at render time, allowing us to remove excess blurring.
• Score: 56.46810752790842
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In rendering, a camera is a sampling operator that maps each finite pixel to a bundle of rays. Different camera models change the geometry of this bundle, thus making a unified and faithful rendering formulation challenging. Consequently, Gaussian ray tracing supports generic cameras (with optical center) through their inverse ray mappings, yet typically reduces every pixel to a single center ray. This ignores the camera-dependent pixel footprint, causing aliasing under minification, while unconstrained Gaussians expose unsupported frequencies under magnification. We present ConeGaussian, a camera-model-agnostic anti-aliasing framework for Gaussian ray-based rendering. Instead of defining the pixel filter on a camera-specific image plane, ConeGaussian constructs an anisotropic footprint directly from neighboring rays produced by the camera's native inverse mapping. We derive a closed-form response under a locally linear, depth-local, moment-matched approximation of the finite pixel footprint, while the same geometry defines a per-Gaussian training-frequency floor. Notably, by construction, our filtering principle can be used unmodified across calibrated central camera models and multiple Gaussian ray-rendering backbones. Additionally, unlike in mip-splatting, our scene-space frequency floor and filtering enable trivial composition at render time, allowing us to remove excess blurring. On pinhole and strongly distorted fisheye captures, ConeGaussian consistently improves two distinct ray-based backbones, by up to 4.3 dB at 1/8 resolution, and reduces fisheye LPIPS by 30% where perspective screen-plane footprint formulations are not directly applicable.

Related papers

• 3D Gaussian Accelerated Ray Tracing: Fast training through particle-based backward propagation [0.00270839927451854]
  We present 3DGART, a practical training framework for ray-traced Gaussian rendering.<n>Our key idea is to reorganise backward propagation around primitives rather than pixels.<n>On Mip-NeRF 360, 3DGART achieves an $approx 3-3.5times$ raw training speedup over per-pixel baseline.
  arXiv  Detail & Related papers  (2026-08-18T02:50:46Z)
• UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras [23.37105294238413]
  UniTriSplat is a unified 3DGS framework for universal cameras that reformulates Gaussian splatting on the unit sphere via HEALPix discretization.<n>We derive the forward rendering and gradient propagation of Gaussians directly in the spherical radian domain, yielding uniform optimization behavior from narrow-FoV images to full 360-degree panoramas.
  arXiv  Detail & Related papers  (2026-06-29T05:14:48Z)
• iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion [62.09575122593993]
  iGaussian is a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion.<n> Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T&T+DB datasets demonstrate a significant performance improvement over previous methods.
  arXiv  Detail & Related papers  (2025-11-18T05:22:22Z)
• 3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting [15.124165321341646]
  We propose 3D Gaussian Unscented Transform (3DGUT), replacing the EWA splatting splatting with the Unscented Transform.<n>This enables the support of distorted time dependent effects such as rolling shutter, while retaining the efficiency of trivialization.
  arXiv  Detail & Related papers  (2024-12-17T03:21:25Z)
• Projecting Gaussian Ellipsoids While Avoiding Affine Projection Approximation [1.4792750204228]
  3D Gaussian Splatting has dominated novel-view synthesis with its real-time rendering speed and state-of-the-art rendering quality. We introduce an ellipsoid-based projection method to calculate the projection of Gaussian ellipsoid onto the image plane, which is the primitive of 3D Gaussian Splatting. Experiments over multiple widely adopted benchmark datasets show that our ellipsoid-based projection method can enhance the rendering quality of 3D Gaussian Splatting and its extensions.
  arXiv  Detail & Related papers  (2024-11-12T06:29:48Z)
• EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis [72.53316783628803]
  We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering.<n>Unlike recentization based approach by 3D Gaussian Splatting (3DGS), our primitive based representation allows for exact volume rendering.<n>We show that our method is more accurate with blending issues than 3DGS and follow-up work on view rendering.
  arXiv  Detail & Related papers  (2024-10-02T17:59:09Z)
• 3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes [50.36933474990516]
  This work considers ray tracing the particles, building a bounding volume hierarchy and casting a ray for each pixel using high-performance ray tracing hardware. To efficiently handle large numbers of semi-transparent particles, we describe a specialized algorithm which encapsulates particles with bounding meshes. Experiments demonstrate the speed and accuracy of our approach, as well as several applications in computer graphics and vision.
  arXiv  Detail & Related papers  (2024-07-09T17:59:30Z)
• Multiscale Representation for Real-Time Anti-Aliasing Neural Rendering [84.37776381343662]
  Mip-NeRF proposes a multiscale representation as a conical frustum to encode scale information. We propose mip voxel grids (Mip-VoG), an explicit multiscale representation for real-time anti-aliasing rendering. Our approach is the first to offer multiscale training and real-time anti-aliasing rendering simultaneously.
  arXiv  Detail & Related papers  (2023-04-20T04:05:22Z)
• Self-Calibrating Neural Radiance Fields [68.64327335620708]
  We jointly learn the geometry of the scene and the accurate camera parameters without any calibration objects. Our camera model consists of a pinhole model, a fourth order radial distortion, and a generic noise model that can learn arbitrary non-linear camera distortions.
  arXiv  Detail & Related papers  (2021-08-31T13:34:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.