StyLandGAN: A StyleGAN based Landscape Image Synthesis using Depth-map
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 35 references that are in the map. First posted on arXiv 13 May 2022.
Builds on
32 of 35 references.
References · 32
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2022Generative Adversarial Networkscited by 5,627
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2021Zero-Shot Text-to-Image Generationcited by 4,288
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
- 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,179
- 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
- 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
- 2016Generative Adversarial Text to Image Synthesiscited by 735
20 more
- 2018Which Training Methods for GANs do actually Converge?cited by 679
- 2020In-Domain GAN Inversion for Real Image Editingcited by 420
- 2017Toward Multimodal Image-to-Image Translationcited by 296
- 2019SEAN: Image Synthesis with Semantic Region-Adaptive Normalizationcited by 253
- 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
- 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 240
- 2020Swapping Autoencoder for Deep Image Manipulationcited by 215
- 2019U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translationcited by 186
- 2020You Only Need Adversarial Supervision for Semantic Image Synthesiscited by 129
- 2020Cross-domain Correspondence Learning for Exemplar-based Image Translationcited by 116
- 2019Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesiscited by 108
- 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
- 2021Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editingcited by 91
- 2018SketchyGAN: Towards Diverse and Realistic Sketch to Image Synthesiscited by 81
- 2021Multimodal Conditional Image Synthesis with Product-of-Experts GANscited by 75
- 2019Learning Single Camera Depth Estimation using Dual-Pixelscited by 49
- 2020COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encodercited by 39
- 2020Why Do Line Drawings Work? A Realism Hypothesiscited by 28
- 2020DeepLandscape: Adversarial Modeling of Landscape Videocited by 17
- 2021Harnessing the Conditioning Sensorium for Improved Image Translationcited by 3
Built on by
Citing papers per year: 2024: 1.
1 paper.