Skip to content
View assembler3d's full-sized avatar

Block or report assembler3d

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
assembler3d/README.md

Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion

   

Wang Zhao1, Yan-Pei Cao2, Jiale Xu1, Yuejiang Dong1,3, 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".

βš™οΈ 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

πŸš€ 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.

Popular repositories Loading

  1. assembler3d assembler3d Public

    Code release of "Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion".

    Python 105 3

  2. assembler3d.github.io assembler3d.github.io Public

    JavaScript