"Zero-Shot" Point Cloud Upsampling
Not on the map. Why?
Abstract (arXiv)
Recent supervised point cloud upsampling methods are restricted by the size of training data and are limited in terms of covering all object shapes. Besides the challenges faced due to data acquisition, the networks also struggle to generalize on unseen records. In this paper, we present an internal point cloud upsampling approach at a holistic level referred to as "Zero-Shot" Point Cloud Upsampling (ZSPU). Our approach is data agnostic and relies solely on the internal information provided by a particular point cloud without patching in both self-training and testing phases. This single-stream design significantly reduces the training time by learning the relation between low resolution (LR) point clouds and their high (original) resolution (HR) counterparts. This association will then provide super resolution (SR) outputs when original point clouds are loaded as input. ZSPU achieves competitive/superior quantitative and qualitative performances on benchmark datasets when compared with other upsampling methods.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 36 of its 53 references that are in the map. First posted on arXiv 25 Jun 2021.
Builds on
36 of 53 references.
References · 36
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2014Conditional Generative Adversarial Netscited by 2,162
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 347
- 2017"Zero-Shot" Super-Resolution using Deep Internal Learningcited by 286
- 2020Single Image Super-Resolution via a Holistic Attention Networkcited by 265
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
- 2018PU-Net: Point Cloud Upsampling Networkcited by 209
- 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
- 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
24 more
- 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
- 2019Image Super-Resolution by Neural Texture Transfercited by 120
- 2020Meta-Transfer Learning for Zero-Shot Super-Resolutioncited by 116
- 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
- 2019Zoom To Learn, Learn To Zoomcited by 115
- 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
- 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
- 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
- 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
- 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
- 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
- 2019Camera Lens Super-Resolutioncited by 56
- 2020Fast Adaptation to Super-Resolution Networks via Meta-Learningcited by 46
- 2019Towards Real Scene Super-Resolution with Raw Imagescited by 44
- 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
- 2019Transductive Zero-Shot Learning for 3D Point Cloud Classificationcited by 39
- 2019Transductive Zero-Shot Learning with Visual Structure Constraintcited by 36
- 2019Zero-shot Learning of 3D Point Cloud Objectscited by 34
- 2016Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learningcited by 20
- 2019Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learningcited by 20
- 2019Zero-shot Learning via Simultaneous Generating and Learningcited by 17
- 2018Learning Class Prototypes via Structure Alignment for Zero-Shot Recognitioncited by 14
- 2019Point Cloud Super Resolution with Adversarial Residual Graph Networkscited by 13
- 2019GeoNet: Deep Geodesic Networks for Point Cloud Analysiscited by 11
Built on by
Citing papers per year: 2021: 1; 2022: 0; 2023: 1; 2024: 1.
3 papers.