janusch

Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

Web Presentation of the Lichtfeld Studio

CPP Implementation of "LightGlue: Local Feature Matching at Light Speed"

3D Gaussian Splat Editor

CUDA and C++ implementation of a Neural Network architecture training CUDA

This project is a CUDA and libtorch-based template, intended to serve as a starting point for high performance computing and machine learning projects on NVIDIA GPUs. It uses Google Test as a testing framework to test against libtorch.

CPP Implementation of "ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation"

CUDA accelerated rasterization of gaussian splatting

Optmized Fused-SSIM

Test plugin for Lichtfeld

LCC data format white paper

GLOMAP - Global Structured-from-Motion Revisited

Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

Fully Fused Differentiable Bilateral Grid

Parrot is a C++ library for fused array operations using CUDA/Thrust. It provides efficient GPU-accelerated operations with lazy evaluation semantics, allowing for chaining of operations without unnecessary intermediate materializations.

Densify a colmap using depth map

You like pytorch? You like micrograd? You love tinygrad! ❤️

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

CLI tool for 3D Gaussian splat format conversion and transformation

LLM training in simple, raw C/CUDA

Code for "LiftFeat: 3D Geometry-Aware Local Feature Matching", ICRA2025

Some information about parameters and options available in COLMAP - SfM & MVS software. https://colmap.github.io

Cuda support lib for GM fit, volume renderer and convolution networks

MVGS: Multi-View Regulated Gaussian Splatting for Novel View Synthesis

Cuda stroke provides some math for fluffy point clouds (Gaussian mixtures)

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

[SIGGRAPH 2025 Conference Paper] Virtualized 3D Gaussians (V3DG)

[WACV 2025] OmniGS: Fast Radiance Field Reconstruction using Omnidirectional Gaussian Splatting