KiloNeRF, MERF, Binary Opacity Grids. PhD Student @ Uni Tübingen / MPI-IS. Supervised by Andreas Geiger @AutoVisionGroup. Student researcher at Google DeepMind.
Tübingen, Deutschland
Joined October 2010
- Tweets156
- Following1.2K
- Followers1.2K
- Likes398
Pinned Tweet
Are you at #SIGGRAPH2024 and want to learn how to reconstruct meshes from multi-view images that contain details like individual strands of grass? Then come today to the "Radiance Field Processing" session at 2 p.m. in Mile High 1.
binary-opacity-grid.github.i…
Christian Reiser retweeted
At ICLR 2024, we proposed GTA to show that relative positional encodings are better in 3D Vision Transformers. GTA had the shortcoming that it only used extrinsics. Li et. al have now fixed this, incorporating intrinsics as well. Essential advance for 3D Vision Transformers!
For everyone interested in precise 📷camera control 📷 in transformers [e.g., video / world model etc]
Stop settling for Plücker raymaps -- use camera-aware relative PE in your attention layers, like RoPE (for LLMs) but for cameras!
Paper & code: liruilong.cn/prope/
Christian Reiser retweeted
🚀 𝐓𝐫𝐢𝐚𝐧𝐠𝐥𝐞 𝐒𝐩𝐥𝐚𝐭𝐭𝐢𝐧𝐠 𝐟𝐨𝐫 𝐑𝐞𝐚𝐥-𝐓𝐢𝐦𝐞 𝐑𝐚𝐝𝐢𝐚𝐧𝐜𝐞 𝐅𝐢𝐞𝐥𝐝 𝐑𝐞𝐧𝐝𝐞𝐫𝐢𝐧𝐠 is out!
We bring triangles back to the spotlight for photorealistic, real-time novel view synthesis.
arxiv.org/abs/2505.19175
🧵👇
Christian Reiser retweeted
We cooked something exciting up for you! 🧑🍳
Your vision, brought to life: Transform any reference image(s) into videos exactly as you envision them and even star in them yourself.
This has been so much fun to work on with an amazing team: @tkipf, @sserenazz, @YuliaRubanova, @nikoskolot, @acoadmarmon, jieru@, @Roni_Paiss, @ShiranZada, @inbar_mosseri
Christian Reiser retweeted
📣 Excited to share our #CVPR2025 Spotlight paper and my internship project @wayve_ai: SimLingo.
A Vision-Language-Action (VLA) model that achieves state-of-the-art driving performance with language capabilities.
Code: github.com/RenzKa/simlingo
Paper: arxiv.org/abs/2503.09594
Christian Reiser retweeted
📢 New paper @CVPR!
Can meshes capture fuzzy geometry? Volumetric Surfaces uses adaptive textured shells to model hair + fur. It’s fast, looks great, and runs in real time even on budget phones.
🔗 autonomousvision.github.io/v…
📄 arxiv.org/pdf/2409.02482
Christian Reiser retweeted
📢 "StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting" 📢
Project page: github.com/ubc-vision/stocha…
arxiv.org/abs/2503.24366
Introducing sort-free and pop-free stochastic rendering and training of 3D Gaussian.
Christian Reiser retweeted
I just pushed a new paper to arXiv. I realized that a lot of my previous work on robust losses and nerf-y things was dancing around something simpler: a slight tweak to the classic Box-Cox power transform that makes it much more useful and stable. It's this f(x, λ) here:
Christian Reiser retweeted
We're demoing SMERF in the SIGGRAPH experience hall for the next two hours. Come talk to us and fly around some reconstructed houses!
Christian Reiser retweeted
Are you frustrated of intermittently bad depth maps ruining your online pipeline 😫? Wish you could get fast 🚀 reuse of your previously predicted depth frames? Do you want shiny fast SOTA feedforward depth and meshes ✨?
Introducing DoubleTake!
nianticlabs.github.io/double…
Christian Reiser retweeted
Introducing Dream Machine - a next generation video model for creating high quality, realistic shots from text instructions and images using AI. It’s available to everyone today! Try for free here lumalabs.ai/dream-machine #LumaDreamMachine – at Palo Alto, CA
Christian Reiser retweeted
easings.net/ is such a good resource if you ever need to blend between things. Just pick a curve that looks nice, then copy-paste the code.
Christian Reiser retweeted
(1/6)
NeRF vs 3D Gaussians vs 3D Meshes
What's better? It's actually simple: the recent success in photo-realistic 3D reconstruction relies on efficient differentiable volumetric rendering. Rays across aligned images intersect, and we solve through ray integrals for the surface.
SuperGaussian looks fantastic! What I like in particular is that they do not rely on perfectly accurate camera poses since they are rendering their own trajectory from the low-res reconstruction. More info: supergaussian.github.io/
Christian Reiser retweeted
🌟 Create anything in 3D! 🌟 Introducing CAT3D: a new method that generates high-fidelity 3D scenes from any number of real or generated images in one minute, powered by multi-view diffusion models.
w/ lovely coauthors @holynski_, @poolio and an amazing team!
Christian Reiser retweeted
Young scientists regularly ask me for career advice. Academia or industry? Big company or startup? US or Europe? Good scientists in AI disciplines are fortunate to have many choices. But choosing can be stressful. I always give the same advice. 1/10
Christian Reiser retweeted
MeshLRM
Large Reconstruction Model for High-Quality Mesh
We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on
