paper-with-me

홈 › Papers

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

2025-03-11 · In Cho, Youngbeom Yoo, Subin Jeon, Seon Joo Kim

Constructing a compressed latent space through a variational autoencoder (VAE) is the key for efficient 3D diffusion models. This paper introduces COD-VAE, a 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.

📄 PDF Abstract BibTeX arXiv:2503.08737

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Topology-Aware Latent Diffusion for 3D Shape Generation

2024-01-31 · Jiangbei Hu, Ben Fei, Baixin Xu, Fei Hou 외

We introduce a new generative model that combines latent diffusion with persistent homology to create 3D shapes with high diversity, with a special emphasis on their topological characteristics. Our method involves repre…

3D Shape GenerationDiversityNavigate

Deep Active Latent Surfaces for Medical Geometries

2022-06-21 · Patrick M. Jensen, Udaranga Wickramasinghe, Anders B. Dahl, Pascal Fua 외

Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often involves learning a latent representation, …

Variational Autoencoding Molecular Graphs with Denoising Diffusion Probabilistic Model

2023-07-02 · Daiki Koge, Naoaki Ono, Shigehiko Kanaya

In data-driven drug discovery, designing molecular descriptors is a very important task. Deep generative models such as variational autoencoders (VAEs) offer a potential solution by designing descriptors as probabilistic…

DenoisingDrug DiscoveryMolecular Property PredictionProperty Prediction+1

3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models

2023-01-26 · Biao Zhang, Jiapeng Tang, Matthias Niessner, Peter Wonka

We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents …

3D Shape RepresentationPoint Cloud Completion

A Mesh Is Worth 512 Numbers: Spectral-domain Diffusion Modeling for High-dimension Shape Generation

2025-03-09 · Jiajie Fan, Amal Trigui, Andrea Bonfanti, Felix Dietrich 외

Recent advancements in learning latent codes derived from high-dimensional shapes have demonstrated impressive outcomes in 3D generative modeling. Traditionally, these approaches employ a trained autoencoder to acquire a…

GPU