Search papers, labs, and topics across Lattice.
UniMesh is introduced as a unified framework for 3D mesh understanding and generation, addressing the limitations of isolated models. It uses a novel Mesh Head to bridge diffusion-based image generation with implicit shape decoders and introduces Chain of Mesh (CoM) for iterative, user-driven semantic mesh editing. Furthermore, UniMesh incorporates a self-reflection mechanism for diagnosing and correcting failures in high-level tasks like 3D captioning, demonstrating competitive performance and novel capabilities.
Forget fragmented architectures: UniMesh lets you edit 3D meshes iteratively with semantic prompts, bridging the gap between generation and understanding.
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.
