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 $128\times$. 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 $16.1\times$ 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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Iqbal, M., Sha, X., Chiba, N., Uranishi, Y., & Mashita, T. (2026). OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots. https://omanscience.com/en/articles/optimusmesh-compact-autoregressive-mesh-generation-from-point-clouds-via-sparse-latent-pivots
MLA 9
Iqbal, Mazhar, et al. "OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots." https://omanscience.com/en/articles/optimusmesh-compact-autoregressive-mesh-generation-from-point-clouds-via-sparse-latent-pivots.
Chicago (author–date)
Iqbal, Mazhar, Xuanmeng Sha, Naoya Chiba, Yuki Uranishi, and Tomohiro Mashita. 2026. "OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots." https://omanscience.com/en/articles/optimusmesh-compact-autoregressive-mesh-generation-from-point-clouds-via-sparse-latent-pivots.
Harvard
Iqbal, M., Sha, X., Chiba, N., Uranishi, Y. and Mashita, T. (2026) 'OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots', Available at: https://omanscience.com/en/articles/optimusmesh-compact-autoregressive-mesh-generation-from-point-clouds-via-sparse-latent-pivots.
Vancouver
Iqbal M, Sha X, Chiba N, Uranishi Y, Mashita T. OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots. https://omanscience.com/en/articles/optimusmesh-compact-autoregressive-mesh-generation-from-point-clouds-via-sparse-latent-pivots
IEEE
M. Iqbal, X. Sha, N. Chiba, Y. Uranishi, and T. Mashita, "OptimusMesh: Compact Autoregressive Mesh Generation from Point Clouds via Sparse Latent Pivots," https://omanscience.com/en/articles/optimusmesh-compact-autoregressive-mesh-generation-from-point-clouds-via-sparse-latent-pivots.