Aug 14, 2017 · We introduce a generative model of part-segmented 3D objects: the shape variational auto-encoder (ShapeVAE). The ShapeVAE describes a joint distribution over the …

Aug 1, 2017 · We introduce a generative model of part-segmented 3D objects: the shape variational auto-encoder (ShapeVAE). The ShapeVAE describes a joint distribution over the …

We introduce a generative model of part-segmented 3D objects: the shape variational auto-encoder (ShapeVAE). The ShapeVAE describes a joint distribution over the existence of …

Mar 27, 2024 · The proposed framework for generative design of 3D chairs introduces a novel, automated approach through a variational autoencoder model and 3D convolutional neural …

The proposed framework for generative de-sign of 3D chairs introduces a novel, automated approach through a variational autoencoder model and 3D convolutional neural network, …

We introduce a generative model of part-segmented 3D objects: the shape variational auto-encoder (ShapeVAE). The ShapeVAE describes a joint distribution over the existence of …

We introduce SDM-NET, a deep generative neural network which produces structured deformable meshes. Specifically, the network is trained to generate a spatial arrangement of closed, …

In this work we present the shape variational auto-encoder (Shape-VAE), a model of structural and local shape variability that captures a distribution over the co-existence of object parts, the …

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 representa-tion of …

To address these challenges, we propose a deep generative model that encodes these relationships as soft constraints on an attributed graph (e.g., the nodes capture attributes of …