3DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Cameras

Zixun Huang, Cho-Ying Wu, Yuliang Guo, Xinyu Huang, Liu Ren

Keywords: Volumetric Rendering, Differentiable Rendering, Novel View Synthesis, Radiance Fields, Neural Reconstruction

TL;DR: Can Gaussian rendering be both exact and fast without relying on lossy splatting? Checkout our 3D-GEER!

Abstract:

3D Gaussian Splatting (3DGS) achieves an appealing balance between rendering quality and efficiency, but relies on approximating 3D Gaussians as 2D projections—an assumption that degrades accuracy, especially under generic large field-of-view (FoV) cameras.
Despite recent extensions, no prior work has simultaneously achieved both projective exactness and real-time efficiency for general cameras. We introduce 3DGEER, a geometrically exact and efficient Gaussian rendering framework. From first principles, we derive a closed-form expression for integrating Gaussian density along a ray, enabling precise forward rendering and differentiable optimization under arbitrary camera models. To retain efficiency, we propose the Particle Bounding Frustum (PBF), which provides tight ray–Gaussian association without BVH traversal, and the Bipolar Equiangular Projection (BEAP), which unifies FoV representations, accelerates association, and improves reconstruction quality. Experiments on both pinhole and fisheye datasets show that 3DGEER outperforms prior methods across all metrics, runs 5x faster than existing projective exact ray-based baselines, and generalizes to wider FoVs unseen during training—establishing a new state of the art in real-time radiance field rendering.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 1163