This is the tf.keras implementation of the volumetric variational autoencoder (VAE) described in the paper "Generative and Discriminative Voxel Modeling with Convolutional Neural Networks".

Nov 24, 2021 · In this paper, we propose an intuitive yet effective self-supervised approach to train a 3D shape variational autoencoder (VAE) which encourages a disentangled latent representation of identity features.

We present Dora-VAE for high-quality 3D reconstruction, and Dora-Bench for 3D VAE evaluation. The improved reconstruction quality offered by Dora-VAE can directly boost the performance ceiling of diffusion models, enabling higher-quality generation results under the …

Variational autoencoders (VAEs) play an important role in high-dimensional data generation based on their ability to fuse the stochastic data representation with the power of recent deep learning techniques.

3d_very_deep_vae PyTorch implementation of (a streamlined version of) Rewon Child's 'very deep' variational autoencoder (Child, R., 2021) for generating synthetic three-dimensional images based on neuroimaging training data.

This is an implementation of the VQ-VAE (Vector Quantized Variational Autoencoder) and Convolutional Varational Autoencoder. from Neural Discrete representation learning for …

Geometry VAE. The key to generating high-quality 3D scenes with a latent diffusion model is our Geometry VAE, capable of compressing pointmaps with high accuracy. We find empirically that our VAE with a transformer decoder is more appropriate for autoencoding pointmaps than a VAE with a convolutional decoder or a VAE pre-trained for ...

Mar 27, 2025 · Abstract: Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while other approaches struggle with high resolutions. ... (VAE) and a rectified flow transformer for ...

Mar 20, 2025 · 3D shape generation has greatly flourished through the development of so-called "native" 3D diffusion, particularly through the Vecset Diffusion Model (VDM). While recent advancements have shown promising results in generating high-resolution 3D shapes, VDM still struggles with high-speed generation. Challenges exist because of difficulties not only in accelerating diffusion sampling but also ...

This study produces the VP model based on a Three-Dimensional Variational Auto Encoder (3D VAE). The proposed model builds all layers depending on 3D convolutional layers. This leads to better extraction of spatiotemporal information and decreases the design complexity.