Joshua Meyer 🥑

Joshua Meyer

PhD Student at Saarland University

I am a PhD student in computer science at Saarland University as a member of the Neuroexplicit Research Group and, with my research, I aim to enhance the safety and robustness of artificial intelligence agents. Before having started here, I did my Bachelor's and Master's Degree in computer graphics under the supervision of Prof. Philipp Slusallek.

 

In my spare time, I love to go hiking and enjoy a variety of sports, including badminton and bouldering. Of course I also very much like playing board and video games. My little plants and bonsais have a special place in my heart🪴. If you ask nicely you might even get pictures of them! On this website, you can find a blog about topics I find interesting and a list of my publications.

Download CV

Recent Posts

    Teaser

    MARS: Multi-sample Allocation through Russian roulette and Splitting

    Abstract Multiple importance sampling (MIS) is an indispensable tool in rendering that constructs robust sampling strategies by combining the respective strengths of individual distributions. Its efficiency can be greatly improved by carefully selecting the number of samples drawn from each distribution, but automating this process remains a challenging problem. Existing works are mostly limited to mixture sampling, in which only a single sample is drawn in total, and the works that do investigate multi-sample MIS only optimize the sample counts at a per-pixel level, which cannot account for variations beyond the first bounce. Recent work on Russian roulette and splitting has demonstrated how fixed-point schemes can be used to spatially vary sample counts to optimize image efficiency but is limited to choosing the same number of samples across all sampling strategies. Our work proposes a highly flexible sample allocation strategy that bridges the gap between these areas of work. We show how to iteratively optimize the sample counts to maximize the efficiency of the rendered image using a lightweight data structure, which allows us to make local and individual decisions per technique. We demonstrate the benefits of our approach in two applications, path guiding and bidirectional path tracing, in both of which we achieve consistent and substantial speedups over the respective previous state-of-the-art.

    27. October, 2024 · Modified: 23. February, 2025 · Joshua Meyer

Education

  1. PhD Computer Science – Artificial Intelligence

    Saarland University

    My PhD research focuses on developing Reinforcement Learning (RL) techniques, with a particular emphasis on improving exploration in model-free settings through advanced sampling strategies. I am also working on enhancing the safety of RL agents by incorporating additional safety mechanisms.
    My work aims to accelerate the learning efficiency of RL agents, while also ensuring that they are more reliable and safer for deployment in real-world, safety-critical applications.

    Co-supervised by Prof. Verena Wolf and Prof. Philipp Slusallek.

  2. MSc Computer Science – Computer Graphics

    Saarland University

    MARS: Multi-sample Allocation through Russian roulette and Splitting.

    Published and presented at Siggraph Asia 2024.
    Supervised by Prof. Philipp Slusallek.

    Grade: 1.0
    Thesis Grade: 1.0
    Read Thesis
  3. BSc Computer Science – Computer Graphics & Artificial Intelligence

    Saarland University

    Integrating a Denoiser into a Renderer using a High-level Language and Partial Evaluation.

    Supervised by Prof. Philipp Slusallek.

    Grade: 1.5
    Thesis Grade: 1.0
  4. German A-levels – Abitur

    Max-Planck-Gymnasium Saarlouis
    Grade: 1.4

Skills & Hobbies

Technical Skills

Linux (Fedora)

The best OS out there

C++

Does exactly what it’s told to. Simple perfection

Python

Concise, yet so inefficient. Give me back control, pretty please

Hobbies

Tea and Coffee

A good morning starts with great tea or coffee

Photography

Enjoy the process – capture the moment!

Hiking

A must as a German, especially through the mountains

Languages

C2
Deutsch
C2
English
B2
Español
A2
Français
A1
日本語