Linus Franke

I am a postdoctoral researcher at Inria Sophia-Antipolis, France in the GraphDeco group with George Drettakis. Before that, I completed my PhD under the supervision of Marc Stamminger at the Chair of Visual Computing of the Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany.

linus (dot) franke (at) inria (dot) fr  /  Scholar  /  Bluesky  /  Twitter  /  Github

Research

Research interest in computer graphics, perceptual rendering, computer vision and machine learning. Current primar focus in neural rendering and novel view synthesis. Representative papers are highlighted.

Enhancing Gaussian Splatting for multi-spectral renderings (e.g. red-edge, near-infrared) with a joint color band neural emissive function.

Exploration of multi-spectral capturings in Gaussian Splatting systems. (*) Denotes equal contribution.

Dense and multi-view consitent depth maps optimized from an monoscopically estimated initialization.

Faster INPC training and rendering with less VRAM and better quality.

Foveated radiance field rendering with smooth Gaussian peripheral and neural point splats for crisp foveal rendering.

Implicit volume-based scene reconstruction combined with point rendering for high detail novel-view synthesis.

A perspective-correct and view-consistent approach for 3D Gaussian splatting accelerated through hybrid transparency.

Rendering and optimizing neural point clouds via trilinear point splatting and tiny neural networks for novel-view synthesis.

Improving point-based novel view synthesis quality by completing point cloud with 3D error volumes from 2D error maps.

Point-based novel view synthesis without per scene preprocessing or training using neural image based rendering. (*) Denotes equal contribution.

Novel view synthesis on live RGB-D streams with feedback during capturing, robust to slam loop closures.

Rendering only relevant fragments for parallax-based light field displays through device-tailored projection matrices.

Point-based differentiable one-pixel point rendering for automatic scene calibration and high-quality novel view synthesis.

Foveated Rendering via temporal forward reprojection for fast, imperceptible VR rendering.

A multi-layered depth of field method for simulating partial occlusion in real-time rendering.

Exploration of generative programming for efficient CUDA kernels in depth of field rendering.

Single-layer tiled splatting for depth of field rendering.

Thanks to Jon Barron for his great template.