MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

TL;DR

MeshCoder is a novel framework that uses large language models and expressive Blender Python APIs to reconstruct complex 3D objects from point clouds into editable scripts, enabling advanced shape editing and understanding.

Contribution

It introduces a comprehensive API set, constructs a large-scale dataset, and trains an LLM for accurate 3D shape-to-code reconstruction, surpassing existing methods.

Findings

Achieves superior shape-to-code reconstruction performance.

Enables intuitive geometric and topological editing.

Enhances 3D shape understanding through code-based reasoning.

Abstract

Reconstructing 3D objects into editable programs is pivotal for applications like reverse engineering and shape editing. However, existing methods often rely on limited domain-specific languages (DSLs) and small-scale datasets, restricting their ability to model complex geometries and structures. To address these challenges, we introduce MeshCoder, a novel framework that reconstructs complex 3D objects from point clouds into editable Blender Python scripts. We develop a comprehensive set of expressive Blender Python APIs capable of synthesizing intricate geometries. Leveraging these APIs, we construct a large-scale paired object-code dataset, where the code for each object is decomposed into distinct semantic parts. Subsequently, we train a multimodal large language model (LLM) that translates 3D point cloud into executable Blender Python scripts. Our approach not only achieves superior performance in shape-to-code reconstruction tasks but also facilitates intuitive geometric and topological editing through convenient code modifications. Furthermore, our code-based representation enhances the reasoning capabilities of LLMs in 3D shape understanding tasks. Together, these contributions establish MeshCoder as a powerful and flexible solution for programmatic 3D shape reconstruction and understanding. The project homepage is available at \href{https://daibingquan.github.io/MeshCoder}{this link}.