paper-with-me

Papers

StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map

2022-05-13 · GunHee Lee, Jonghwa Yim, Chanran Kim, Minjae Kim

Despite recent success in conditional image synthesis, prevalent input conditions such as semantics and edges are not clear enough to express Linear (Ridges)' and Planar (Scale)' representations. To address this problem, we propose a novel framework StyLandGAN, which synthesizes desired landscape images using a depth map which has higher expressive power. Our StyleLandGAN is extended from the unconditional generation model to accept input conditions. We also propose a '2-phase inference' pipeline which generates diverse depth maps and shifts local parts so that it can easily reflect user's intend. As a comparison, we modified the existing semantic image synthesis models to accept a depth map as well. Experimental results show that our method is superior to existing methods in quality, diversity, and depth-accuracy.

📄 PDF Abstract BibTeX arXiv:2205.06611

Code (0)

등록된 구현이 없습니다.

Tasks

DiversityImage Generation

Similar Papers 제목 키워드 기반

Rethinking Image Skip Connections in StyleGAN2

2024-07-08 · Seung Park, Yong-Goo Shin

Various models based on StyleGAN have gained significant traction in the field of image synthesis, attributed to their robust training stability and superior performances. Within the StyleGAN framework, the adoption of i…

Image Generation

3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images

2021-07-20 · SungMin Hong, Razvan Marinescu, Adrian V. Dalca, Anna K. Bonkhoff 외

Image synthesis via Generative Adversarial Networks (GANs) of three-dimensional (3D) medical images has great potential that can be extended to many medical applications, such as, image enhancement and disease progressio…

Generative Adversarial NetworkImage EnhancementImage Generation

StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN

2024-03-21 · CVPR 2024 1 · Jongwoo Choi, Kwanggyoon Seo, Amirsaman Ashtari, Junyong Noh

We propose a method that can generate cinemagraphs automatically from a still landscape image using a pre-trained StyleGAN. Inspired by the success of recent unconditional video generation, we leverage a powerful pre-tra…

Unconditional Video GenerationVideo Generation

DeepLandscape: Adversarial Modeling of Landscape Video

2020-08-21 · Elizaveta Logacheva, Roman Suvorov, Oleg Khomenko, Anton Mashikhin 외

We build a new model of landscape videos that can be trained on a mixture of static landscape images as well as landscape animations. Our architecture extends StyleGAN model by augmenting it with parts that allow to mode…

DeepLandscape: Adversarial Modeling of Landscape Videos

2020-08-01 · ECCV 2020 8 · Elizaveta Logacheva, Roman Suvorov, Oleg Khomenko, Anton Mashikhin 외

We build a new model of landscape videos that can be trained on a mixture of static landscape images as well as landscape animations. Our architecture extends StyleGAN model by augmenting it with parts that allow to mode…

Video Generation