LinPrim: Linear Primitives for Differentiable Volumetric Rendering

A new Radiance Field representation has been published by the Technical University of Munich.

A new Radiance Field representation has been published by the Technical University of Munich.

Michael Rubloff

Michael Rubloff

Michael is the Founder and Managing Editor of Radiancefields.com

LinPrim

Radiance field representations have experienced explosive growth over the last five years. Now, researchers from the Technical University of Munich have introduced a compelling new radiance field approach called LinPrim, or Linear Primitives for Differentiable Volumetric Rendering. Developed by Nicolas von Lützow and Matthias Niessner, LinPrim leverages simple yet powerful geometric primitives, octahedra and tetrahedra, for differentiable volumetric rendering. The method promises high-fidelity reconstructions and a framework that is both intuitive and integrative with traditional 3D graphics workflows.

LinPrim takes a different approach from Gaussian Splatting by introducing explicit linear polyhedral primitives as a foundation for volumetric scene representation. These primitives offer bounded geometries that are easier to manipulate and more aligned with traditional graphics techniques. LinPrim’s use of bounded polyhedral primitives challenges the conventional reliance on continuous or Gaussian-based representations in NVS.

LinPrim uses two types of geometric primitives: octahedra (shapes with eight triangular faces) and tetrahedra (four-sided triangular pyramids). These primitives serve as the building blocks for reconstructing 3D scenes. Each primitive is defined by its position, rotation, vertex distances, opacity, and view-dependent color.

Octahedra leverages inherent symmetries to minimize the number of parameters required to describe their geometry. For example, the distances to opposing vertices are shared, ensuring stability and reducing computational complexity. Tetrahedra, while slightly more complex, also follows a simplified parameterization scheme.

The rendering process uses a GPU-optimized, fully differentiable rasterizer. This enables gradient-based optimization, allowing primitives to adjust their features (e.g., geometry, position, and color) to match input images. 

Despite being highly expressive, LinPrim achieves interactive frame rates by relying on straightforward geometric calculations, such as ray-triangle intersections.  Additionally, they are also able to reduce memory consumption by using fewer primitives to represent the scene while maintaining similar visual fidelity to Gaussian Splatting.

Its workflow consists of three key stages: primitive initialization, differentiable rendering, and optimization. LinPrim begins by using Structure-from-Motion (SfM) to extract and initialize 3D points from input images. Each SfM point is used to initialize a primitive (octahedron or tetrahedron) with a fixed position, size, and rotation. The primitives are processed to determine how they interact with rays cast from a virtual camera. Ray intersections are calculated with the triangular faces of the primitives and used to compute opacity and color.

The process is fully differentiable, allowing errors in rendered images to propagate back to the primitives’ geometric parameters. Using gradient descent, LinPrim adjusts the positions, shapes, and colors of its primitives to minimize differences between rendered and input images. Additionally, the system dynamically adds or removes primitives to ensure an optimal balance between scene complexity and fidelity. LinPrim also incorporates advanced anti-aliasing techniques to reduce visual artifacts.

In terms of rendering speed, LinPrim can achieve real-time performance, hitting frame rates of up to 68 frames per second for octahedra-based scenes and 175 fps for tetrahedra-based scenes on an NVIDIA RTX 3090 GPU. The tests occurred on the ScanNet++ & Mip-NeRF 360 datasets. While there’s not an explicit mention of how much VRAM LinPrim consumes, the fact that it can fit on consumer cards bodes well for the new Radiance Field method.

There’s no word yet on a potential code release or licensing information, but we will be closely monitoring the paper. We’re entering an exciting period where I believe we will see more novel radiance field methods. The original paper can be found here.

Thumbnail for Gaussian Splatting News episode 13

13:12

Watch · New every Monday

The Biggest Week Yet for Gaussian Splatting: Blender + Unreal

Episode 13 · Nov 16, 2026

Blender 5.3 is out, and Gaussian splats are now a native part of it: PLY and SPZ files import as their own point cloud type and render in EEVEE, Cycles and Workbench, with no add-on.

Featured

Recents

News

ASU Open Sources Open4DGS for Genlock-Free 4D Gaussian Splatting

Open4DGS from Arizona State University turns consumer multi-camera video into 4D Gaussian splats, using a sub-frame sync solver in place of hardware genlock.

Michael Rubloff

Nov 18, 2026

News

ASU Open Sources Open4DGS for Genlock-Free 4D Gaussian Splatting

Open4DGS from Arizona State University turns consumer multi-camera video into 4D Gaussian splats, using a sub-frame sync solver in place of hardware genlock.

Michael Rubloff

Platforms

ANNX Studio 1.6.1 Brings MCMC and Xsplat Training to Mac

ANNX Studio 1.6.1 brings MCMC, Xsplat and Default (gsplat) training to Apple Silicon Macs and adds a live preview for inspecting each model as it trains.

Michael Rubloff

Nov 18, 2026

Platforms

ANNX Studio 1.6.1 Brings MCMC and Xsplat Training to Mac

ANNX Studio 1.6.1 brings MCMC, Xsplat and Default (gsplat) training to Apple Silicon Macs and adds a live preview for inspecting each model as it trains.

Michael Rubloff

Platforms

Esri Makes ArcGIS Reality Server Generally Available

ArcGIS Reality Server is generally available with ArcGIS Enterprise 12.2, adding self-hosted, distributed processing of drone imagery into Gaussian splats.

Michael Rubloff

Nov 18, 2026

Platforms

Esri Makes ArcGIS Reality Server Generally Available

ArcGIS Reality Server is generally available with ArcGIS Enterprise 12.2, adding self-hosted, distributed processing of drone imagery into Gaussian splats.

Michael Rubloff

News

Cornell Tech's Pentimento Takes ACADIA'26 Best Paper

Pentimento from Cornell Tech and CITA won Best Paper at ACADIA'26, registering smart-glasses video splats to a design model to document reclaimed-timber builds.

Michael Rubloff

Nov 18, 2026

News

Cornell Tech's Pentimento Takes ACADIA'26 Best Paper

Pentimento from Cornell Tech and CITA won Best Paper at ACADIA'26, registering smart-glasses video splats to a design model to document reclaimed-timber builds.

Michael Rubloff

Trending Articles
  1. TRENDING
    Loading...
  2. TRENDING
    Loading...
  3. TRENDING
    Loading...
Michael Rubloff

Written by Michael Rubloff

Michael is the Founder and Managing Editor of Radiancefields.com

More from Michael Rubloff

More from Michael Rubloff

News

ASU Open Sources Open4DGS for Genlock-Free 4D Gaussian Splatting

Open4DGS from Arizona State University turns consumer multi-camera video into 4D Gaussian splats, using a sub-frame sync solver in place of hardware genlock.

Michael Rubloff

Nov 18, 2026

Open4DGS

News

ASU Open Sources Open4DGS for Genlock-Free 4D Gaussian Splatting

Michael Rubloff

Nov 18, 2026

Open4DGS

News

ASU Open Sources Open4DGS for Genlock-Free 4D Gaussian Splatting

Open4DGS from Arizona State University turns consumer multi-camera video into 4D Gaussian splats, using a sub-frame sync solver in place of hardware genlock.

Michael Rubloff

Nov 18, 2026

Open4DGS

Platforms

ANNX Studio 1.6.1 Brings MCMC and Xsplat Training to Mac

ANNX Studio 1.6.1 brings MCMC, Xsplat and Default (gsplat) training to Apple Silicon Macs and adds a live preview for inspecting each model as it trains.

Michael Rubloff

Nov 18, 2026

A Gaussian splat reconstruction of a traditional Korean pavilion, from the ANNX Studio website

Platforms

ANNX Studio 1.6.1 Brings MCMC and Xsplat Training to Mac

Michael Rubloff

Nov 18, 2026

A Gaussian splat reconstruction of a traditional Korean pavilion, from the ANNX Studio website

Platforms

ANNX Studio 1.6.1 Brings MCMC and Xsplat Training to Mac

ANNX Studio 1.6.1 brings MCMC, Xsplat and Default (gsplat) training to Apple Silicon Macs and adds a live preview for inspecting each model as it trains.

Michael Rubloff

Nov 18, 2026

A Gaussian splat reconstruction of a traditional Korean pavilion, from the ANNX Studio website

Platforms

Esri Makes ArcGIS Reality Server Generally Available

ArcGIS Reality Server is generally available with ArcGIS Enterprise 12.2, adding self-hosted, distributed processing of drone imagery into Gaussian splats.

Michael Rubloff

Nov 18, 2026

An Esri graphic showing a 3D reality-mapped city with a diagram of ArcGIS Pro sending processing from ArcGIS Enterprise to ArcGIS Reality Server

Platforms

Esri Makes ArcGIS Reality Server Generally Available

Michael Rubloff

Nov 18, 2026

An Esri graphic showing a 3D reality-mapped city with a diagram of ArcGIS Pro sending processing from ArcGIS Enterprise to ArcGIS Reality Server

Platforms

Esri Makes ArcGIS Reality Server Generally Available

ArcGIS Reality Server is generally available with ArcGIS Enterprise 12.2, adding self-hosted, distributed processing of drone imagery into Gaussian splats.

Michael Rubloff

Nov 18, 2026

An Esri graphic showing a 3D reality-mapped city with a diagram of ArcGIS Pro sending processing from ArcGIS Enterprise to ArcGIS Reality Server

New to Gaussian Splatting? Start here

Radiance fields, explained from the ground up: what a Gaussian splat is, how to capture one, and which tools and gear to start with.

Newsletter

Keep up with the field.

New research, tools and captures from the Radiance Fields newsroom, in your inbox. Free, no spam.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.

Gaussian Splatting News on YouTube

The week in radiance fields, every Monday.