OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots

arXiv:2610.01148v1 Announce Type: new Abstract: Generating compact and geometrically faithful 3D meshes directly from point clouds remains a fundamental challenge. Point clouds are unordered and sparse, whereas meshes exhibit irregular structure and varying topology. As a result, many existing approaches rely on implicit representations followed by surface extraction or reconstruction. Although effective, these pipelines can produce dense or over-smoothed meshes, often requiring computationally expensive post-processing and simplification. We present OptimusMesh, a framework for direct compact triangle mesh generation from point clouds using sparse latent pivot conditioning. Our key idea is to compress 2{,}048 oriented input points into only 16 sparse latent pivots, reducing the geometric conditioning set by 128imes. These pivots provide a compact structural representation shared across a two-stage autoregressive framework that first generates mesh vertices and then predicts triangular faces conditioned on the generated vertices and the same pivots. Compared with the evaluated recent point-cloud-conditioned autoregressive methods, which use 257 decoder-conditioning tokens, OptimusMesh uses only 16, yielding a 16.1imes shorter conditioning sequence. Experiments show that OptimusMesh produces the most compact outputs among the compared recent autoregressive methods, using 25.7%--94.1% fewer faces while maintaining competitive geometric fidelity and distributional quality.

Related

• Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
• SubdivAR: Autoregressive Next-Scale Prediction for Neural Mesh Subdivision
• Nexus: Native Mesh Generation with Diffusion

Source: arXiv cs.CV | 2026-10-02