English
Related papers

Related papers: EpiGRAF: Rethinking training of 3D GANs

200 papers

Synthesis and reconstruction of 3D human head has gained increasing interests in computer vision and computer graphics recently. Existing state-of-the-art 3D generative adversarial networks (GANs) for 3D human head synthesis are either…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Sizhe An , Hongyi Xu , Yichun Shi , Guoxian Song , Umit Ogras , Linjie Luo

Generative Adversarial Networks have been employed successfully to generate high-resolution augmented images of size 1024^2. Although the augmented images generated are unprecedented, the training time of the model is exceptionally high.…

Image and Video Processing · Electrical Eng. & Systems 2022-02-28 Atharva Karwande , Pranesh Kulkarni , Tejas Kolhe , Akshay Joshi , Soham Kamble

Score-based generative models (SGMs) have recently emerged as a promising class of generative models. The key idea is to produce high-quality images by recurrently adding Gaussian noises and gradients to a Gaussian sample until converging…

Computer Vision and Pattern Recognition · Computer Science 2022-06-13 Hengyuan Ma , Li Zhang , Xiatian Zhu , Jingfeng Zhang , Jianfeng Feng

Existing 3D-from-2D generators are typically designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-03 Ivan Skorokhodov , Aliaksandr Siarohin , Yinghao Xu , Jian Ren , Hsin-Ying Lee , Peter Wonka , Sergey Tulyakov

Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization. However, existing training procedures are limited to images of low resolution (typically below 32x32), and…

Machine Learning · Computer Science 2020-10-27 Yang Song , Stefano Ermon

We propose a new approach for high resolution semantic image synthesis. It consists of one base image generator and multiple class-specific generators. The base generator generates high quality images based on a segmentation map. To further…

Computer Vision and Pattern Recognition · Computer Science 2021-10-11 Yuheng Li , Yijun Li , Jingwan Lu , Eli Shechtman , Yong Jae Lee , Krishna Kumar Singh

3D-aware Generative Adversarial Networks (GANs) have shown remarkable progress in learning to generate multi-view-consistent images and 3D geometries of scenes from collections of 2D images via neural volume rendering. Yet, the significant…

Computer Vision and Pattern Recognition · Computer Science 2024-01-05 Alex Trevithick , Matthew Chan , Towaki Takikawa , Umar Iqbal , Shalini De Mello , Manmohan Chandraker , Ravi Ramamoorthi , Koki Nagano

Training of Generative Adversarial Network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation. In general, the computational cost of training GAN scales exponentially with…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Masaki Saito , Shunta Saito , Masanori Koyama , Sosuke Kobayashi

Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning. Although recent advances have shown promise in learning 3D models from 2D images, these methods…

Computer Vision and Pattern Recognition · Computer Science 2024-02-05 Qijia Shen , Guangrun Wang

Emergent capabilities of image generators have led to many impactful zero- or few-shot applications. Inspired by this success, we investigate whether video generators similarly exhibit 3D-awareness. Using structure-from-motion as a 3D-aware…

Computer Vision and Pattern Recognition · Computer Science 2025-03-28 Chun-Hao Paul Huang , Niloy Mitra , Hyeonho Jeong , Jae Shin Yoon , Duygu Ceylan

Existing methods for 3D-aware image synthesis largely depend on the 3D pose distribution pre-estimated on the training set. An inaccurate estimation may mislead the model into learning faulty geometry. This work proposes PoF3D that frees…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Zifan Shi , Yujun Shen , Yinghao Xu , Sida Peng , Yiyi Liao , Sheng Guo , Qifeng Chen , Dit-Yan Yeung

Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors. Recently, the integration of Neural Radiance Fields (NeRFs) and…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Mohamad Shahbazi , Evangelos Ntavelis , Alessio Tonioni , Edo Collins , Danda Pani Paudel , Martin Danelljan , Luc Van Gool

3D GAN inversion aims to project a single image into the latent space of a 3D Generative Adversarial Network (GAN), thereby achieving 3D geometry reconstruction. While there exist encoders that achieve good results in 3D GAN inversion, they…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Bahri Batuhan Bilecen , Ahmet Berke Gokmen , Aysegul Dundar

Neural volume rendering techniques, such as NeRF, have revolutionized 3D-aware image synthesis by enabling the generation of images of a single scene or object from various camera poses. However, the high computational cost of NeRF presents…

Computer Vision and Pattern Recognition · Computer Science 2025-01-20 Peng Zheng , Linzhi Huang , Yizhou Yu , Yi Chang , Yilin Wang , Rui Ma

Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…

Machine Learning · Computer Science 2020-07-02 Zijun Zhang , Ruixiang Zhang , Zongpeng Li , Yoshua Bengio , Liam Paull

Generative Adversarial Networks (GAN) have many potential medical imaging applications, including data augmentation, domain adaptation, and model explanation. Due to the limited memory of Graphical Processing Units (GPUs), most current 3D…

Image and Video Processing · Electrical Eng. & Systems 2022-09-13 Li Sun , Junxiang Chen , Yanwu Xu , Mingming Gong , Ke Yu , Kayhan Batmanghelich

Modern 3D-GANs synthesize geometry and texture by training on large-scale datasets with a consistent structure. Training such models on stylized, artistic data, with often unknown, highly variable geometry, and camera information has not…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Rameen Abdal , Hsin-Ying Lee , Peihao Zhu , Menglei Chai , Aliaksandr Siarohin , Peter Wonka , Sergey Tulyakov

Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency. 3D-aware GAN methods can maintain view consistency but their…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Jingxiang Sun , Xuan Wang , Yong Zhang , Xiaoyu Li , Qi Zhang , Yebin Liu , Jue Wang

We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions. The generator of…

Computer Vision and Pattern Recognition · Computer Science 2022-12-14 Hao Liu , Hui Yuan , Junhui Hou , Raouf Hamzaoui , Wei Gao

We describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively: starting from a low resolution, we add new layers that model increasingly fine details…

Neural and Evolutionary Computing · Computer Science 2018-02-28 Tero Karras , Timo Aila , Samuli Laine , Jaakko Lehtinen