3D GANs and Latent Space: A comprehensive survey
Not on the map. Why?
Abstract (arXiv)
Generative Adversarial Networks (GANs) have emerged as a significant player in generative modeling by mapping lower-dimensional random noise to higher-dimensional spaces. These networks have been used to generate high-resolution images and 3D objects. The efficient modeling of 3D objects and human faces is crucial in the development process of 3D graphical environments such as games or simulations. 3D GANs are a new type of generative model used for 3D reconstruction, point cloud reconstruction, and 3D semantic scene completion. The choice of distribution for noise is critical as it represents the latent space. Understanding a GAN's latent space is essential for fine-tuning the generated samples, as demonstrated by the morphing of semantically meaningful parts of images. In this work, we explore the latent space and 3D GANs, examine several GAN variants and training methods to gain insights into improving 3D GAN training, and suggest potential future directions for further research.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 126 of its 173 references that are in the map. First posted on arXiv 8 Apr 2023.
Builds on
126 of 173 references.
References · 126
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,213
- 2022Generative Adversarial Networkscited by 5,614
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,975
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,257
- 2017Improved Training of Wasserstein GANscited by 2,226
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,225
- 2014Conditional Generative Adversarial Netscited by 2,157
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,051
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,906
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,178
38 more
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2018Self-Attention Generative Adversarial Networkscited by 809
- 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
- 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 697
- 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 692
- 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
- 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 671
- 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
- 2021Score-based Generative Modeling in Latent Spacecited by 635
- 2017Generative Adversarial Networks: An Overviewcited by 589
- 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
- 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
- 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 505
- 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 490
- 2021GAN Inversion: A Surveycited by 366
- 2019DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesiscited by 308
- 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
- 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
- 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
- 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 260
- 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
- 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 231
- 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
- 2018Pros and Cons of GAN Evaluation Measurescited by 224
- 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
- 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
- 2021Projected GANs Converge Fastercited by 207
- 20193D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutionscited by 173
- 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 170
- 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
- 2020DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesiscited by 161
- 2019ManiGAN: Text-Guided Image Manipulationcited by 156
- 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
- 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
- 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
- 2017BEGAN: Boundary Equilibrium Generative Adversarial Networkscited by 121
- 2016Energy-based Generative Adversarial Networkcited by 119
- 2017The Cramer Distance as a Solution to Biased Wasserstein Gradientscited by 116
50 most cited of 126 All 126 (JSON)
Built on by
Citing papers per year: 2025: 1.
1 paper.