zxhuang1698/ZeroShape
Code repository for "ZeroShape: Regression-based Zero-shot Shape Reconstruction".
This project helps you create a detailed 3D model of an object from just a single 2D image. You input an image and, optionally, a mask showing the object's outline, and it outputs a complete 3D shape, even for objects it hasn't seen before. This tool is for researchers and developers working on computer vision tasks that require generating 3D representations from 2D photos.
137 stars. No commits in the last 6 months.
Use this if you need to generate realistic 3D models of various objects from individual 2D pictures without needing extensive pre-existing 3D data for each object.
Not ideal if you are a non-technical user looking for a point-and-click solution for 3D modeling, as it requires familiarity with command-line operations and Python environments.
Stars
137
Forks
20
Language
Python
License
—
Category
Last pushed
Jul 18, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zxhuang1698/ZeroShape"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openspyrit/spyrit
A Python toolbox for deep image reconstruction, with emphasis on single-pixel imaging.
RobotLocomotion/pytorch-dense-correspondence
Code for "Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation"
Fyusion/LLFF
Code release for Local Light Field Fusion at SIGGRAPH 2019
pmh47/dirt
DIRT: a fast differentiable renderer for TensorFlow
marrlab/SHAPR_torch
SHAPR: Code for "Capturing Shape Information with Multi-Scale Topological Loss Terms for 3D...