提出新型网格压缩方法，实现超8000面网格高效生成。
Scaling Mesh Generation via Compressive Tokenization
- 采用分块索引与局部聚合压缩网格序列
- 序列长度减少约75%，支持超8000面网格生成
- 可直接用于点云/图像控制生成，适合工业级应用
我们提出一种高效且压缩的网格表示方法——分块与分片标记化（BPT），实现了超过8000个面的网格生成。BPT通过分块索引和局部区域聚合，使网格序列长度相比原始序列减少约75%。这一压缩突破使得高面数网格数据得以利用，显著提升生成细节丰富度与鲁棒性。基于BPT，我们构建了在大规模网格数据上训练的基础网格生成模型，支持点云与图像的灵活控制。该模型能够生成具有精细细节和准确拓扑结构的网格，在网格生成任务中达到当前最优性能，具备直接投入产品使用的潜力。
原文摘要 · Abstract (English)
We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。