Representing 3D Shapes with 64 Latent Vectors for 3D Diffusion Models

Seon Kim, Subin Jeon, In Cho, Youngbeom Yoo

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• join16/COD-VAE

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 16× compression compared to the baseline while maintaining quality. This enables 20.8× 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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2503.08737")
get_code_for_paper("2503.08737")
have("2503.08737")

Connect an agent — have() is free.