Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion

   

Wang Zhao¹, Yan-Pei Cao², Jiale Xu¹, Yuejiang Dong^1,3, Ying Shan¹

¹ARC Lab, Tencent PCG   ²VAST   ³Tsinghua University

SIGGRAPH ASIA 2025

---

🚩 Overview

This repository contains code release for our SIGGRAPH ASIA 2025 paper "Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion".

⚙️ Installation

We recommend using anaconda to install the dependencies:

conda create -n assembler python=3.10.16
conda activate assembler
conda install pytorch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 pytorch-cuda=12.4 -c pytorch -c nvidia
pip install -r requirements.txt

🚀 Usage

Inference

To run the inference demo, simply use:

python ./scripts/demo.py --config ./configs/demo/demo.yaml --input_dir ./examples/4ef447cbb4a72f0a0e5941c9073c4baa0babd3f93ec55d62b040915f8bf3f49c --output_dir ./outputs/4ef447

This script runs for example data inside ./examples from Toys4k dataset. You could use your own data to assemble. Put all the part meshes (in GLB format) and reference image (in PNG format) into a single folder, and set the input_dir argument to that folder.