Lakonik/SSDNeRF
[ICCV 2023] Single-Stage Diffusion NeRF
This tool helps 3D content creators and researchers generate realistic 3D objects or reconstruct them from limited 2D views. It takes various 3D datasets (like cars, chairs, or tables) or single 2D images as input and produces high-fidelity 3D models and novel views. Individuals working in 3D graphics, virtual reality, or generative AI will find this useful for creating and manipulating 3D assets.
447 stars. No commits in the last 6 months.
Use this if you need to generate high-quality 3D models of objects or reconstruct a 3D scene from just a few images, aiming for realistic details and novel view synthesis.
Not ideal if you are looking for a simple, out-of-the-box solution for non-technical users, as it requires familiarity with Python, CUDA, and specific data preprocessing.
Stars
447
Forks
25
Language
Python
License
MIT
Category
Last pushed
Apr 20, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Lakonik/SSDNeRF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jayin92/Skyfall-GS
Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
Tencent-Hunyuan/Hunyuan3D-2
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
ActiveVisionLab/gaussctrl
[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing
caiyuanhao1998/Open-DiffusionGS
Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D...
deepseek-ai/DreamCraft3D
[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with...