UniMesh: Unifying 3D Mesh Understanding and Generation

TL;DR

UniMesh is a unified 3D framework that combines understanding and generation tasks, enabling iterative editing, improved performance, and knowledge transfer in 3D scene modeling.

Contribution

It introduces a Mesh Head for cross-model interfacing, Chain of Mesh for iterative semantic editing, and a self reflection mechanism for high-level task diagnosis.

Findings

Achieves competitive benchmarks in 3D understanding and generation.

Enables user-driven semantic mesh editing through Chain of Mesh.

Demonstrates improved performance via self reflection and iterative reasoning.

Abstract

Recent advances in 3D vision have led to specialized models for either 3D understanding (e.g., shape classification, segmentation, reconstruction) or 3D generation (e.g., synthesis, completion, and editing). However, these tasks are often tackled in isolation, resulting in fragmented architectures and representations that hinder knowledge transfer and holistic scene modeling. To address these challenges, we propose UniMesh, a unified framework that jointly learns 3D generation and understanding within a single architecture. First, we introduce a novel Mesh Head that acts as a cross model interface, bridging diffusion based image generation with implicit shape decoders. Second, we develop Chain of Mesh (CoM), a geometric instantiation of iterative reasoning that enables user driven semantic mesh editing through a closed loop latent, prompting, and re generation cycle. Third, we incorporate a self reflection mechanism based on an Actor Evaluator Self reflection triad to diagnose and correct failures in high level tasks like 3D captioning. Experimental results demonstrate that UniMesh not only achieves competitive performance on standard benchmarks but also unlocks novel capabilities in iterative editing and mutual enhancement between generation and understanding. Code: https://github.com/AIGeeksGroup/UniMesh. Website: https://aigeeksgroup.github.io/UniMesh.