yyeboah/Awesome-Text-to-3D

A growing curation of Text-to-3D, Diffusion-to-3D works.

What it solves

Text-to-3D and diffusion-to-3D research is growing quickly, but papers, code, and project pages are scattered. This project provides a single, well-organized index so researchers can find relevant work fast without digging through many separate sources.

How it works

Entries are grouped by task (like X-to-3D, 3D editing, avatars, dynamic content, world models) and by content type. Each paper links to its BibTeX citation, project site, and code when available. The list also tracks citation counts using Semantic Scholar, helping you gauge how influential a paper is within the indexed set.

Who it's for

Researchers, students, and developers working on or exploring 3D generation from text or diffusion models. It's also useful for anyone who wants a quick overview of the latest work in this area.

Highlights

  • First curated list of text-to-3D and diffusion-to-3D research
  • Organized by task and content type for fast browsing
  • Links to BibTeX, project pages, and code when available
  • Citation counts from Semantic Scholar to show impact
  • Covers X-to-3D, 3D editing, animations, avatars, and world models
  • Includes datasets, frameworks, and tutorial videos

Related

  • Project
    naver/anny

    Anny is an open‑source, PyTorch‑based differentiable human‑body mesh model covering all ages. It offers multiple rigs (compact 104‑bone default, full MakeHuman), several mesh topologies (including SMPL‑X and SOMA), and fine‑grained shape, local‑change, and facial‑action parameters. Install via pip, run a quick Python example to output a .ply mesh, or launch an interactive Gradio demo. The library is Apache‑2.0 licensed, builds on MakeHuman assets, and is intended for research/production tasks such as pose estimation, animation, and cross‑age body modeling.

  • Project
    Eyeline-Labs/Vista4D

    Vista4D is a video reshooting framework that uses 4D point clouds to synthesize dynamic scenes from source videos using novel camera trajectories and viewpoints.

  • Project
    hi3d-official/Hi3Dv1.0

    Hi3D v1.0 is a GPU-only 3D geometry refinement tool: it takes a coarse mesh plus a reference image and produces a high-detail mesh through 1–3 progressive refinement passes (up to 1536³ effective resolution). It ships inference code only, requires Linux/Python 3.10/NVIDIA GPU with CUDA 12.x, and is licensed under a custom agreement permitting commercial use with branding and scale-based license triggers.

  • Project
    Shpigford/nurb

    nurb is a locally‑run Python/macOS app that lets you describe a 3‑D part in plain language, has your existing LLM write real B‑Rep CAD code, checks the model against 13 print‑ability rules, shows live updates in a three.js viewer, and exports print‑ready 3MF (or STL/STEP/GLB) with slicer settings embedded.