paper-with-me

Papers

Don't Mesh with Me: Generating Constructive Solid Geometry Instead of Meshes by Fine-Tuning a Code-Generation LLM

2024-11-22 · Maximilian Mews, Ansar Aynetdinov, Vivian Schiller, Peter Eisert, Alan Akbik

While recent advancements in machine learning, such as LLMs, are revolutionizing software development and creative industries, they have had minimal impact on engineers designing mechanical parts, which remains largely a manual process. Existing approaches to generating 3D geometry most commonly use meshes as a 3D representation. While meshes are suitable for assets in video games or animations, they lack sufficient precision and adaptability for mechanical engineering purposes. This paper introduces a novel approach for the generation of 3D geometry that generates surface-based Constructive Solid Geometry (CSG) by leveraging a code-generation LLM. First, we create a dataset of 3D mechanical parts represented as code scripts by converting Boundary Representation geometry (BREP) into CSG-based Python scripts. Second, we create annotations in natural language using GPT-4. The resulting dataset is used to fine-tune a code-generation LLM. The fine-tuned LLM can complete geometries based on positional input and natural language in a plausible way, demonstrating geometric understanding.

📄 PDF Abstract BibTeX arXiv:2411.15279

Code (0)

등록된 구현이 없습니다.

Tasks

3D geometryCode Generation

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Adam 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree

2020-12-01 · NeurIPS 2020 12 · Kacper Kania, Maciej Zieba, Tomasz Kajdanowicz

Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods that are based on such representation achieved state-of-the-art 3D shape reconstruction quality. However, these methods struggle to…

3D Shape Reconstruction

UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree

2020-06-16 · Kacper Kania, Maciej Zięba, Tomasz Kajdanowicz

Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods that are based on such representation achieved state-of-the-art 3D shape reconstruction quality. However, these methods struggle to…

3D Shape Reconstruction

DiffCSG: Differentiable CSG via Rasterization

2024-09-02 · Haocheng Yuan, Adrien Bousseau, Hao Pan, Chengquan Zhang 외

Differentiable rendering is a key ingredient for inverse rendering and machine learning, as it allows to optimize scene parameters (shape, materials, lighting) to best fit target images. Differentiable rendering requires…

Inverse Rendering

CSGNet: Neural Shape Parser for Constructive Solid Geometry

2017-12-22 · CVPR 2018 6 · Gopal Sharma, Rishabh Goyal, Difan Liu, Evangelos Kalogerakis 외

We present a neural architecture that takes as input a 2D or 3D shape and outputs a program that generates the shape. The instructions in our program are based on constructive solid geometry principles, i.e., a set of bo…

MeshReGen: A Unified 3D Geometry Regeneration Framework

2026-04-30 · Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan, Jong Chul Ye 외 arxiv

We consider the problem of regenerating 3D objects from 2D images and initial 3D shapes. Most 3D generators operate in a one-shot fashion, converting text or images to a 3D object with limited controllability. We introdu…

3D Generation