janusch

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.

A curated directory of research papers, open-source tools, viewers, and tutorials about 3D Gaussian Splatting, a technique for turning photos or video frames into interactive, photorealistic 3D scenes.

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

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

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

Optmized Fused-SSIM

Web Presentation of the Lichtfeld Studio

CUDA accelerated rasterization of gaussian splatting

GLOMAP - Global Structured-from-Motion Revisited

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

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.

Test plugin for Lichtfeld

Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo (TPAMI 2022)

A render engine for NeRFs!

[CVPR 2026] 4C4D: 4 Camera 4D Gaussian Splatting

Official implementation of Gaussian point splatting (SIGGRAPH'26)

Densify a colmap using depth map

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

LCC data format white paper

Fully Fused Differentiable Bilateral Grid

CLI tool for 3D Gaussian splat format conversion and transformation

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

Script for preprocceing the Neural 3D Video dataset on a frame basis

🎮 A step-by-step guide to implementing SSAO, depth of field, lighting, normal mapping, and more for your 3D game.

No description.

[T-RO 2026] Bundle Adjustment in the Eager Mode

GRay: Ray Tracing 3D Gaussians Near the Speed of Splats

No description.

3D Gaussian Splat Editor

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

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.

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.

LLM training in simple, raw C/CUDA

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

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

Edit gaussian splatting models

Plenoxels: Radiance Fields without Neural Networks

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian(Published in SIGGRAPH Asia 2024)

Unofficial implementation of 3D Gaussian Splatting in PyTorch + CUDA with MIT license

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

[NeurIPS 2024] Generalizable and Animatable Gaussian Head Avatar

OpenGL demo of a point rendering and texture filtering technique called Surface Splatting.

A library of C++ coroutine abstractions for the coroutines TS

computer vision stuff

Hot shit interpreter

A cheatsheet of modern C++ language and library features.

Repo for me dotfiles

unix-like reverse engineering framework and commandline tools

No description.

No description.

No description.

No description.