用64个潜在向量高效压缩3D形状，提升生成速度与质量。
Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models
- 分两阶段编码：先压缩点云为紧凑向量，再用三平面解码提升效率。
- 相比基线实现16倍压缩，生成速度提升20.8倍，质量无损。
- 自适应剪枝机制，仅在复杂区域计算，节省资源适合部署。
通过变分自编码器（VAE）构建压缩潜在空间是实现高效3D扩散模型的关键。本文提出COD-VAE，将3D形状编码为一组紧凑的1维潜在向量，同时保持高质量重建。COD-VAE采用两阶段自编码架构：首先，编码器块通过中间点块逐步压缩点云为紧凑潜在向量；其次，基于三平面的解码器从潜在向量重构密集三平面，而非直接解码神经场，显著降低神经场解码的计算开销。最后，提出不确定性引导的令牌剪枝策略，通过跳过简单区域的计算，自适应分配资源以提升解码效率。实验表明，COD-VAE相比基线实现16倍压缩，生成速度提升20.8倍，且质量未下降。结果说明，大量潜在向量并非高质量重建的必要条件。代码已开源：https://github.com/join16/COD-VAE。
原文摘要 · Abstract (English)
Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE that encodes 3D shapes into a COmpact set of 1D latent vectors without sacrificing quality. COD-VAE introduces a two-stage autoencoder scheme to improve compression and decoding efficiency. First, our encoder block progressively compresses point clouds into compact latent vectors via intermediate point patches. Second, our triplane-based decoder reconstructs dense triplanes from latent vectors instead of directly decoding neural fields, significantly reducing computational overhead of neural fields decoding. Finally, we propose uncertainty-guided token pruning, which allocates resources adaptively by skipping computations in simpler regions and improves the decoder efficiency. Experimental results demonstrate that COD-VAE achieves 16x compression compared to the baseline while maintaining quality. This enables 20.8x speedup in generation, highlighting that a large number of latent vectors is not a prerequisite for high-quality reconstruction and generation. The code is available at https://github.com/join16/COD-VAE.
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。