paper-with-me

Papers

3D GANs and Latent Space: A comprehensive survey

2023-04-08 · Satya Pratheek Tata, Subhankar Mishra

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.

📄 PDF Abstract BibTeX arXiv:2304.03932

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction3D Semantic Scene CompletionPoint cloud reconstructionSurvey

Similar Papers 제목 키워드 기반

A Comprehensive Survey on Data-Efficient GANs in Image Generation

2022-04-18 · Ziqiang Li, Beihao Xia, Jing Zhang, Chaoyue Wang 외

Generative Adversarial Networks (GANs) have achieved remarkable achievements in image synthesis. These successes of GANs rely on large scale datasets, requiring too much cost. With limited training data, how to stable th…

Image GenerationSurvey

Image Generation and Recognition (Emotions)

2019-10-13 · Hanne Carlsson, Dimitrios Kollias

Generative Adversarial Networks (GANs) were proposed in 2014 by Goodfellow et al., and have since been extended into multiple computer vision applications. This report provides a thorough survey of recent GAN research, o…

Image Generation

Revisiting Latent Space of GAN Inversion for Real Image Editing

2023-07-18 · Kai Katsumata, Duc Minh Vo, Bei Liu, Hideki Nakayama

The exploration of the latent space in StyleGANs and GAN inversion exemplify impressive real-world image editing, yet the trade-off between reconstruction quality and editing quality remains an open problem. In this stud…

Unsupervised Image Generation with Infinite Generative Adversarial Networks

2021-08-18 · ICCV 2021 10 · Hui Ying, He Wang, Tianjia Shao, Yin Yang 외

Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision. Generative Adversarial Networks (…

Image Generation

Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey

2023-02-17 · Shiv Ram Dubey, Satish Kumar Singh

Generative Adversarial Networks (GANs) have been very successful for synthesizing the images in a given dataset. The artificially generated images by GANs are very realistic. The GANs have shown potential usability in se…

Image GenerationImage-to-Image TranslationTranslation