Our new Gaussian point splatting renders huge 3DGS scenes in real time (e.g. 425 M⬇️). It samples pixel-sized points from the Gaussians with massive parallelism and splats them to the screen using 64-bit atomics. Grab @SIGGRAPH 2026 paper code video now: jorisar.nl/gaussian_point_sp…

RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting Contributions: • We introduce a unified surface-volume Gaussian scene representation for jointly modeling sharp specular reflections and clear transmission in real-world scenes containing thin semi-transparent surfaces. • We propose Specular-Aware Gradient Gating to suppress misleading gradients from complex specular regions, substantially reducing floaters in the transmission branch. • Extensive experiments demonstrate that RT-Splatting significantly outperforms prior methods while maintaining real-time rendering and enabling flexible scene editing.

3 major SuperSplat upgrades shipping today 🚀 🧱 One-Click Collision Generation We've wired the SplatTransform 2.0 collision pipeline into SuperSplat Studio's backend. Open your splat ➡️ Assets panel ➡️ Hit Generate Walk-ready splats in seconds. No command line. No fuss. [1 / 4]

Massive VRAM improvements and 8K training are coming to LichtFeld Studio. Since the last nightly build, you can already experience major VRAM improvements based on this wonderful paper: "VkSplat: High-Performance 3DGS Training in Vulkan Compute" This enables uncapped training, which will be merged today and made available in the next nightly builds to all current supporters. If you haven’t already, please consider supporting the project. Bronze sponsoring, for instance, costs much less than a yearly paid subscription to closed-source competitors, offers better quality and many more features, brings your brand onto the homepage, and lets you use LichtFeld Studio forever. Support the project here: portal.lichtfeld.io Image: Training on office2 8k images from the eyefull tower dataset

This January, I decided to give it a shot and wrote my first paper Today, I am happy to share that it was accepted by #SIGGRAPH2026 SAD is a differentiable image representation with soft, anisotropic partitioning, with up to 20x faster encoding time🧵 luckyiyi.github.io/SAD/index…

Release: LichtFeld Studio v0.5.2 is out! With 186 commits to master, this release is mainly focused on bug fixes and usability improvements. What’s new in v0.5.2: - Histogram cleanup improvements - HDR image maps for rendering - Background color picker - Visualization of loss per camera - Training evaluation now also works in the UI - Free orbit and FPV camera modes - Dockable sequencer and histogram - Continued migration from ImGui to RmlUi for HTML- and CSS-like formatting and styling This release is available to all supporters as a Windows binary via portal.lichtfeld.io. At the same time, LichtFeld Studio remains committed to being free and open source under GPLv3, and it can also be built from source. Please consider supporting the ongoing development of LichtFeld Studio through a donation via the portal. That support has already enabled the first grant to Shady, who will contribute significantly to the upcoming v0.5.3 release. Thank you to everyone who supports this project financially, with code, bug reports, data, website work, and other contributions. With continued support, we hope to expand these grants to support more active contributors to the codebase. A special thank you to our foundational sponsor Core11 and our gold sponsor Volinga, who have helped make the current state of the software possible. Thank you as well to every donor and to all the new bronze sponsors. For v0.5.3, LFS will move the frontend to Vulkan, which is the first step toward vendor-independent GPU support. It will also enable initial path tracing and custom shaders. Planned features also include direct support for the sparkjs rad LoD format and asset management for training data and 3DGS files. You can find links to our main sponsors in the comments. Please visit also the website to explore our new bronze sponsors! Hint: We do not yet have a silver or platinum sponsor. 😉

Gaussian Splatting struggles with high-frequency details. Our #CVPR2026 paper “Neural Gabor Splatting” is out! By augmenting each Gaussian with an MLP that models high-frequency signals, we significantly improve reconstruction quality with fewer primitives.

Learn how MRNF in LichtFeld Studio enables 3D reconstructions in the automotive industry! Watch the full video here: youtu.be/FqYTKeI5K6I?si=65am…

Spark 2.0 is here! 🚀 We’re redefining what’s possible on the web with a streamable LoD system for 3D Gaussian Splatting. Built on Three.js, you can now stream massive 100M splat worlds to any device from mobile to VR using WebGL2. All open-source. Dive into the tech 👇

Heads up: there are some changes coming to LichtFeld Studio. LichtFeld is growing quite a lot, but contributions are not. In fact, besides the two corporate contributors and one bronze sponsor, there is less than $100 on average contributed per month. There were 10,000 downloads in the last 30 days, and nobody contributed anything financially back to the project. Not a single dollar. I cannot support my living on that basis. Given the amount of work I am putting into this project, and it is a lot, often easily 60 hours a week, to provide a state-of-the-art, self-contained 3D reconstruction suite that is used by businesses around the world, this situation is no longer sustainable. The idea was to grow it together, but at the moment it is mainly being used without enough support in return. If every user had contributed only $10, the continuation of the project would have been secured. I have asked for that quite often. I like sharing my knowledge, but I cannot sustain it under these circumstances. Going forward, there will not be any free binaries provided anymore. I created a portal at portal.lichtfeld.io which will give access to daily binaries after registration and donation. This will hopefully help finance the development and maybe even allow me to pay someone in addition. If you cannot afford it, you can still put in the work and build it from source. There are no restrictions. I am aware that people like to work around something like this, and they certainly will. But in the end, that simply means that my work on this project will be discontinued at some point. Btw, after payment an invoice will be automatically issued!

🚀 Neural expressivity meets 3DGS efficiency at #ICLR2026! Our approach matches the rendering quality and speed of 3DGS with ✅ 10x fewer primitives ✅ 6x fewer parameters Jointly led by X. Zhou and @huy_nguyen_bao. 🔗vcai.mpi-inf.mpg.de/projects… 📝arxiv.org/pdf/2510.08491 #3DGS #VR

LichtFeld Studio v0.5.1 released! Upgrading is highly recommended! Highlights: - MRNF densification strategy - NanoGS sparsification - Native File Dialogs on Linux, too - 3DGS USD format import and export support - Depth Mode selection - Viewport Splitting - Make LichtFeld optionally default for 3DGS file formats (ply, sogs, spz, etc) :) - Many Bugfixes (weird edge cases, stability, UI quirks, sparsification, etc) Thanks to every contributor. Special thanks to Core11 GmbH for continuous financial and non-financial support!

Testing my DJI Osmo 360 rig for gaussian splatting. Mason’s Avenue, London. 14 million splats total. Trained with LichtFeld Studio and gsplat, edited in Houdini GSOPs, camera animation in Unity and rendered with Deckard Render. #gaussiansplatting #3DGS

Huge update: LichtFeld Studio v0.5.0 🚀 What’s new: • Embedded Python runtime plugin system makes LFS fully hackable and extensible (isolated uv environments, hot reload) • Integrated plugin marketplace (6 plugins incl. Sharp4D, densification ) • MCP protocol integration (full parity with the user interaction layer) • Mesh rendering OpenMesh (Python) Mesh2Splat • ImprovedGS (arxiv:2603.08661) • RmlUI-based GUI (HTML and CSS style workflows) • Undo/Redo with plugin integration, Sequencer, PPiSP Huge thanks to our corporate sponsor Core11 GmbH and to all contributors 🙏Enjoy! If you find it useful, consider supporting the project by donating to keep it evolving. Next up: better training quality and smoother editing workflows

COLMAP just dropped V4.0, officially adding GLOMAP and several updates.

Our Neural Irradiance Volume (Eurographics 2026) permits real-time rendering of large scenes with dynamic objects and moving lights, while providing a higher quality at a given memory budget (10x improvement over probe grids!). Project page: arnocoomans.be/eg2026/.

Fun fact: if you train a 3D Gaussian splat with images where the subject keeps looking at the camera, you get this... 👀 Runnable link 👇