rundiwu/SingleShapeGen
code for paper "Learning to Generate 3D Shapes from a Single Example", SIGGRAPH Asia 2022
This project helps 3D artists, designers, and researchers generate many new, unique 3D models that share the style and characteristics of a single existing 3D shape. You input one example 3D model, and the system outputs numerous variations, allowing for different resolutions and spatial adjustments. It's ideal for anyone needing to expand a collection of 3D assets based on a specific aesthetic.
No commits in the last 6 months.
Use this if you need to create a large dataset of variations for a specific 3D model, such as for games, virtual reality, or architectural visualization, and you only have one example to start with.
Not ideal if you need to generate 3D shapes from scratch based on text descriptions or images, or if you need to combine features from multiple distinct input shapes.
Stars
98
Forks
12
Language
Python
License
MIT
Category
Last pushed
Feb 22, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/rundiwu/SingleShapeGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)