😮

⚡ Ray Tracing + 3D Gaussians = New Possibilities! Gaussian splatting is limited by rasterization—our #SIGGRAPHAsia2024 paper shows how to ray trace instead, enabling reflections, shadows, fisheye cameras, and more. The most important (and hardest!) part is making it fast. (1/N)

I just released a Slang.D implementation of 3D Gaussian Splatting renderer. This will allow researchers to write 3DGS papers even faster (sigh!) since there is no backward pass! You can trivially change the forward pass like you would do on PyTorch! github.com/google/slang-g…

Awesome work just dropped for high-quality relightable Gaussians. Huge congrats to Yohan Poirier-Ginter !

Here is our shot at reducing artifacts in 3D Gaussian splat rendering. Paper: arxiv.org/abs/2410.08129 Website: fhahlbohm.github.io/htgs/ Code: Planned, but timeline still unknown More info in the thread below.

Our latest work to increase multi-view coherence in 3D Gaussian Splatting using Hybrid Transparency: - Perspective-correct (no affine approximation) and without matrix inversions - Per-pixel sorted (no popping) for the K-nearest fragments ~2x faster than 3DGS Led by Florian Hahlbohm

Hot dang!

The original 3DGS code is an academic research project, the fact that somebody is still actively improving it 1.5 years later is 🧑‍🍳😘 (chef's kiss)

This project blew my mind! It looks just as good as 3DGS but it has no per-scene optimization or reconstruction. Every frame is generated *from scratch* and it nevertheless runs in real-time. quark-3d.github.io

Two days after the h-1b fallout, and 80% of the nazi stuff has vanished from my twitter feed. Interesting?

StochasticSplats: Stochastic Rasterization for Sorting-Free 3D Gaussian Splatting Abstract: 3D Gaussian splatting (3DGS) is a popular radiance field method with many application-specific extensions. Most variants rely on the same core algorithm: depth-sorting of Gaussian splats

We are very excited to announce our work "On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images", to be presented at #SIGGRAPH2025! Learn more: repo-sam.inria.fr/nerphys/on-the… 1/3

Janusch, take the wheel