paper-with-me

Papers

PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes

2019-11-25 · CVPR 2020 6 · Rundi Wu, Yixin Zhuang, Kai Xu, Hao Zhang, Baoquan Chen

We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly. The input to our network is a 3D shape segmented into parts, where each part is first encoded into a feature representation using a part autoencoder. The core component of PQ-NET is a sequence-to-sequence or Seq2Seq autoencoder which encodes a sequence of part features into a latent vector of fixed size, and the decoder reconstructs the 3D shape, one part at a time, resulting in a sequential assembly. The latent space formed by the Seq2Seq encoder encodes both part structure and fine part geometry. The decoder can be adapted to perform several generative tasks including shape autoencoding, interpolation, novel shape generation, and single-view 3D reconstruction, where the generated shapes are all composed of meaningful parts.

📄 PDF Abstract BibTeX arXiv:1911.10949

Code (3)

ChrisWu1997/PQ-NET pytorch
Mistral-Twirl/3D-Point-Cloud-Metrics tf
hailieqh/3d-object-primitive-graph pytorch

Tasks

3D ReconstructionDecoderSingle-View 3D Reconstruction

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Solana Customer Service Number +1-833-534-1729 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks

2017-07-01 · CVPR 2017 7 · Amir Arsalan Soltani, Haibin Huang, Jiajun Wu, Tejas D. Kulkarni 외

We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes; however, voxel-based representations suffer from hig…

Inferring 3D Shapes from Image Collections using Adversarial Networks

2019-06-11 · Matheus Gadelha, Aartika Rai, Subhransu Maji, Rui Wang

We investigate the problem of learning a probabilistic distribution over three-dimensional shapes given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called projective generative a…

Generative Adversarial Network

CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition

2018-11-19 · ICCV 2019 10 · Nadav Schor, Oren Katzir, Hao Zhang, Daniel Cohen-Or

Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks. A reoccurring challenge is how to enable a model to generate a rich variety of samples from the entire target …

Diversity

Multi-chart Generative Surface Modeling

2018-06-06 · Heli Ben-Hamu, Haggai Maron, Itay Kezurer, Gal Avineri 외

This paper introduces a 3D shape generative model based on deep neural networks. A new image-like (i.e., tensor) data representation for genus-zero 3D shapes is devised. It is based on the observation that complicated sh…

3D Shape GenerationTranslation

Unsupervised Primitive Discovery for Improved 3D Generative Modeling

2019-06-09 · CVPR 2019 6 · Salman H. Khan, Yulan Guo, Munawar Hayat, Nick Barnes

3D shape generation is a challenging problem due to the high-dimensional output space and complex part configurations of real-world objects. As a result, existing algorithms experience difficulties in accurate generative…

3D Shape Generation