Lukas Radl
Passionate about digitally representing the physical world
I'm a University Assistant/PhD Student at the Institute of Visual
Computing, Graz University of
Technology.
I work on 3D Scene Representations for View Synthesis, supervised by Markus Steinberger.
Previously, I received my Master's degree in Computer Science (with distinction)
and my
Bachelor's degree in Software Engineering both at Graz
University of Technology between 2018 and 2023.
During this time, I worked as a study assistant, supporting various visual
computing
classes.
In 2019 & 2020, I was featured on the Dean's
List of my faculty (top 5% of students).
|
|
π¬ Research
My research lies at the intersection of
3D, Computer Graphics,
Computer Vision, Machine Learning,
and Parallel Processing:
My recent work focuses on Radiance Field Representations
such as Neural Radiance Fields (NeRF) and
Gaussian Splatting, aiming to make them more practical
for real-time rendering and interactive applications.
|
|
SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction
Lukas Radl,
Felix Windisch,
Thomas Deixelberger,
Jozef Hladky,
Michael Steiner,
Dieter Schmalstieg,
Markus Steinberger.
SIGGRAPH Asia, 2025.
We analyze and improve Gaussian Opacity Fields, and incorporate per-pixel sorting, exact depth and novel losses
to enable rapid extraction of unbounded meshes from 3D Gaussians.
|
|
Image-Based Spatio-Temporal Interpolation for Split
Rendering
Michael Steiner*,
Thomas
KΓΆhler*,
Lukas Radl,
Brian
Budge.
Markus Steinberger.
Computer Graphics Forum, 2025.
We investigate a bidirectional reprojection method for challenging split
rendering scenarios,
and add a dynamic shadow encoding scheme and use auxiliary cameras to handle
occlusions.
|
|
AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian
Rendering
Michael Steiner*,
Thomas
KΓΆhler*,
Lukas Radl,
Felix
Windisch,
Dieter Schmalstieg,
Markus Steinberger.
ICCV, 2025 (Highlight).
We introduce a method for Anti-Aliased and
Artifact-Free (AAA)
Gaussian Rendering, building on per-pixel resorting,
view-adaptive filtering and view-space culling.
|
|
VRSplat: Fast and
Robust Gaussian Splatting for Virtual Reality
Xuechang
Tu,
Lukas Radl,
Michael Steiner,
Markus Steinberger.
Bernhard Kerbl,
Fernando de la Torre.
PACMCGIT, 2025.
We combine StopThePop, Optimal Projection and Mini-Splatting with single-pass
foveated rendering for view-consistent real-time rendering of Gaussian Splats on
HMDs.
|
|
Frustum Volume
Caching for Accelerated NeRF Rendering
Michael Steiner,
Thomas
KΓΆhler,
Lukas Radl,
Markus Steinberger.
PACMCGIT, 2024.
We leverage the architecture of Instant-NGP to cache view-independent latent
codes in a frustum
voxel grid for high-quality real-time and offline rendering.
|
|
StopThePop: Sorted Gaussian Splatting for
View-Consistent Real-time
Rendering
Lukas Radl*,
Michael Steiner*,
Mathias Parger,
Alexander
Weinrauch,
Bernhard Kerbl,
Markus Steinberger.
SIGGRAPH, 2024 (Journal Track).
Sorting 3D Gaussians along view rays leads to increased view-consistency.
With our hierarchical, GPU-friendly resorting scheme, our renderer is only 4%
slower than 3DGS
on average.
|
|
LAENeRF: Local Appearance Editing for Neural Radiance
Fields
Lukas Radl,
Michael Steiner,
Andreas
Kurz,
Markus Steinberger.
CVPR, 2024.
Locally Stylized Neural Radiance Fields via point-based 3D style transfer with
geometry-aware
losses - reduced background artefacts, more detail retention and
view-consistency.
|
|
Analyzing the Internals of Neural Radiance
Fields
Lukas Radl,
Andreas
Kurz,
Michael Steiner,
Markus Steinberger.
CVPR Workshop on Neural Rendering Intelligence, 2024.
Using density estimates derived from activations for inverse transform sampling
in NeRFs
allows for faster inference and comparable visual quality.
|
|
AVT: Multicenter aortic vessel tree CTA dataset collection
with ground
truth segmentation masks
Lukas Radl,
Yuan Jin,
Antonio
Pepe,
Jianning Li,
Christina
Gsaxner,
Fen-hua Zhao,
Jan Egger.
Data in Brief, 2022.
Method and apparatus for aorta segmentation in Slicer3D, as well as an
open-source CTA dataset
with ground-truth annotations, to be used in research.
|
π Reviewing
Since 2024, Iβve had the privilege of serving as a reviewer for
leading journals and conferences in computer graphics and vision:
- β
Computers & Graphics
- β
Computer Graphics Forum (CGF)
- β
IEEE VR
- β
Eurographics
- β
ICCV
- β
Transactions on Visualization and Computer Graphics
|
π Teaching
Iβve been actively involved in teaching a range of visual computing courses.
βοΈ = Summer term, βοΈ = Winter term.
|
Tutoring
Worked as a study assistant: guiding students in exercises, grading, and
interviews.
2022/23
- β
Real-Time Graphics: Exercise βοΈ
- β
Mathematical Principles in Visual Computing: Exercise βοΈ
- β
Computer Graphics: Exercise βοΈ
- β
Computer Vision: Exercise βοΈ
2021/22
- β
Real-Time Graphics: Exercise βοΈ
- β
Computer Graphics: Exercise βοΈ
- β
Computer Vision: Exercise βοΈ
2020/21
- β
Computer Graphics: Exercise βοΈ
- β
Computer Vision: Exercise βοΈ
|
Exercise Coordination
Since starting my PhD, Iβve been coordinating exercises for visual computing
courses.
2025/26
- β
Real-Time Graphics: Exercise βοΈ
- β
Object-Oriented Programming 1: Exercise βοΈ
- β
Writing Scientific Papers: Seminar βοΈ
- β
Computer Graphics: Exercise βοΈ
2024/25
- β
Real-Time Graphics: Exercise βοΈ
- β
Object-Oriented Programming 1: Exercise βοΈ
- β
Writing Scientific Papers: Seminar βοΈ
- β
Computer Graphics: Exercise βοΈ
2023/24
- β
Real-Time Graphics: Exercise βοΈ
- β
Computer Graphics: Exercise βοΈ
|
π Open Student Projects
Our research group is passionate about real-time rendering,
with a special focus on Radiance Fields.
Here are some exciting projects you can get involved in:
|
|
π Currently Open Projects
Interested in joining? Reach out to me (preferably via
email) π§
|
|