google-deepmind/unpic

google-deepmind/unpic

Description: Implementation of unPIC from "How to Spin an Object: First, Get the Shape Right", a CVPRW 2026 paper.

Language: Python

License: Apache-2.0

Stars: 1

Forks: 0

Open issues: 0

Created: 2026-06-04T14:37:24Z

Pushed: 2026-06-04T16:59:53Z

Default branch: main

Fork: no

Archived: no

README:

unPIC

Official implementation of unPIC from How to Spin an Object: First, Get the Shape Right, a CVPRW 2026 paper (link). This repository contains the code to run our hierarchical diffusion model for generating 3D views from a single 2D input.


Getting Started

Follow these steps to set up the project locally.

Prerequisites

• Python 3.8 or later
• An NVIDIA GPU with CUDA support (RTX A4000 or above) is recommended for

performance.

Installation

1. Initialize Git LFS and clone the repository:

git lfs install
git clone https://github.com/google-deepmind/unpic.git
cd unpic

2. Create and activate a virtual environment (Recommended):

python3 -m venv unpic_env
source unpic_env/bin/activate

3. Install dependencies: The required Python packages are listed in pyproject.toml. Install them using pip: pip install .

Usage

You can run inference on a single image using the run_unpic.py script. The script requires a path to an input image, the pre-trained model variables, and an output directory.

Example Command:

python run_unpic.py \
--input_image_path /path/to/your/image.png \
--checkpoint_dir checkpoint/ \
--output_dir /path/to/save/outputs/ \
--config config.py

Citing This Work

@InProceedings{Kabra_2026_CVPR,
author = {Kabra, Rishabh and A Hudson, Drew and van Steenkiste, Sjoerd and Carreira, Joao and Mitra, Niloy J},
title = {How to Spin an Object: First, Get the Shape Right},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2026},
pages = {4708-4718}
}