longxiang-ai/awesome-gaussians

This repository tracks the latest advancements in 3D Gaussian Splatting from Arxiv, with daily automated updates. Stay up-to-date with cutting-edge research in this exciting field!

What it solves

Researchers and practitioners in 3D Gaussian Splatting need to keep up with a rapidly growing body of research. This project solves that by maintaining a constantly updated, categorized index of papers and resources, plus an interactive web atlas to explore trends and connections.

How it works

The list is automatically refreshed daily using a crawler that pulls new papers from arXiv, filters them by configurable keywords and domains, and categorizes them into topics like acceleration, avatar generation, or SLAM. A CLI tool (python main.py) lets users search, suggest keywords, export BibTeX, and regenerate the README. The project also includes an interactive Paper Atlas website built from the collected data, showing monthly trends, topic networks, and co-author networks.

Who it's for

Anyone working on or following Gaussian Splatting research: academics, developers, and hobbyists who want a centralized, up-to-date collection of papers and tools, and the ability to explore and export references.

Highlights

  • Daily automatic updates with resilient crawling (handles API rate limits and outages)
  • Interactive Paper Atlas with paper maps, trends, topic networks, and co-author networks
  • Unified CLI with subcommands for search, suggestions, BibTeX export, and README generation
  • Customizable time ranges, arXiv domain filtering, and smart extraction of links from abstracts

Related

  • Project
    TripoGrowthLab/awesome-astra-prompts

    A curated collection of 358 GPT-6 Astra prompts for building 3D games, scenes, and interactive worlds in Blender, Three.js, Unreal Engine, Unity, and the browser, with entries available in 14 languages and 12 containing source code.

  • Project
    PozzettiAndrea/ComfyUI-Sharp

    A ComfyUI wrapper for Apple's SHARP model that enables monocular 3D Gaussian Splatting from a single image in under one second.

  • Project
    inspatio/querysplat

    QuerySplat is a 3D Gaussian Splatting prediction framework that decouples geometry and appearance representations to improve the quality of 3D scene reconstructions from images.

  • Project
    pwilkin/trellis.cpp

    trellis.cpp is a C++ GGML implementation of Microsoft’s TRELLIS 2‑4B image‑to‑3D pipeline. It converts a single image (or a Stable Diffusion‑generated image) into a fully textured GLB model, running entirely in native C++ with optional GPU back‑ends (CUDA, Vulkan, ROCm, Metal, Qualcomm HTP). It provides a CLI, a Tauri‑based desktop UI (Trellis Studio), and an HTTP server for programmatic use. The repo includes the full pipeline – background removal, three flow‑transformer stages, VAE decoders, mesh extraction, QEM decimation, UV unwrapping and WebP‑compressed PBR textures – and ships pre‑built binaries and GGUF model files.