# luciddreamer-cvlab/LucidDreamer

Official code for the paper "LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes".

Repository: https://github.com/luciddreamer-cvlab/LucidDreamer
Canonical: https://ross.abutalabs.com/products/luciddreamer
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-23T05:35:53+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 35, longevity 72
- inputs: {"age_days": 1015, "days_push": 41, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1528, forks 111 (observed 2026-08-28T04:04:58.659147+00:00)

## What it is
LucidDreamer is the official implementation of a research method that generates 3D Gaussian Splatting scenes from text prompts, published in IEEE TVCG 2025 (Best Paper Runner-Up). It combines diffusion-based image generation with depth estimation and Gaussian splatting to create domain-free 3D scenes.

## Use cases
- generate 3d scenes from text prompts
- create gaussian splatting scenes without domain-specific training
- text to 3d scene generation for research
- produce 3d environments for visualization papers
- generate novel 3d worlds from a description

## When to choose
- you need text-to-3D scene generation with Gaussian splatting
- you are reproducing or building on the LucidDreamer paper
- you want a research-grade pipeline combining diffusion models and 3DGS

## When to avoid
- you need a commercially licensed tool (CC BY-NC-SA 4.0)
- you need production-ready 3D content creation software
- you cannot run CUDA/GPU workloads

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, graphics, simulation
- domain: artificial-intelligence, computer-vision, graphics, deep-learning
- platform: windows, python
- tags: 3d-gaussian-splatting, text-to-3d, scene-generation, diffusion-models, depth-estimation, research-code, non-commercial-license, linux, gpu

## Member repositories
- luciddreamer-cvlab/LucidDreamer (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:58.659147+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:31.011810+00:00, confidence not recorded.
  - readme: https://github.com/luciddreamer-cvlab/LucidDreamer (fetched 2026-08-28T04:04:58.659147+00:00, sha b2409142ac27)
- Data as of 2026-08-30T08:39:29.467469+00:00.