Nicolas von Lützow Profile
Nicolas von Lützow

@nicolasvluetzow

Followers
43
Following
7
Media
0
Statuses
4

PhD Student @ TUM Visual Computing & AI Lab

Joined April 2025
Don't wanna be here? Send us removal request.
@nicolasvluetzow
Nicolas von Lützow
7 days
The code for “LinPrim: Linear Primitives for Differentiable Volumetric Rendering” is now out! 🧩 → Code: https://t.co/4YvQl1NkYf → Paper: https://t.co/VT1yxFA7cv #NeurIPS2025
Tweet card summary image
arxiv.org
Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many...
@nicolasvluetzow
Nicolas von Lützow
1 month
Thrilled to share that our work LinPrim has been accepted to NeurIPS 2025! 🎉 A big thank you to my advisor @MattNiessner for the guidance and support throughout the project! ✨ Also, make sure to check out the other amazing papers from our lab - lots of exciting research! 🚀
0
0
6
@nicolasvluetzow
Nicolas von Lützow
1 month
Thrilled to share that our work LinPrim has been accepted to NeurIPS 2025! 🎉 A big thank you to my advisor @MattNiessner for the guidance and support throughout the project! ✨ Also, make sure to check out the other amazing papers from our lab - lots of exciting research! 🚀
@MattNiessner
Matthias Niessner
1 month
All six of our submissions were accepted to #NeurIPS2025 🎉🥳 Awesome works about Gaussian Splatting Primitives, Lighting Estimation, Texturing, and much more GenAI :) Great work by @Peter4AI, @YujinChen_cv, @ZheningHuang, @jiapeng_tang, @nicolasvluetzow, @jnthnschmdt 🔥🔥🔥
1
0
7
@MattNiessner
Matthias Niessner
1 month
All six of our submissions were accepted to #NeurIPS2025 🎉🥳 Awesome works about Gaussian Splatting Primitives, Lighting Estimation, Texturing, and much more GenAI :) Great work by @Peter4AI, @YujinChen_cv, @ZheningHuang, @jiapeng_tang, @nicolasvluetzow, @jnthnschmdt 🔥🔥🔥
7
24
253
@MattNiessner
Matthias Niessner
6 months
📢 LinPrim: Linear Primitives for Differentiable Volumetric Rendering 📢 We use octahedra or tetrahedra as explicit as volumetric building blocks for gradient-based novel view synthesis - as an alternative to 3D Gaussians with discrete, bounded geometry. We show how it can be
1
33
176