Generation of Synthetic Elevation Models and Realistic Surface Images of River Deltas and Coastal Terrains Using cGANs

Valencia-Rosado, Luis Oswaldo; Guzman-Zavaleta, Zobeida Jezabel; Starostenko, Oleg

doi:10.1109/access.2020.3048083

Cited by 6 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In counterpart, Guérin et al [31] presented a proposal for the generation of mountains and rivers using cGANs with hand-drawn sketches as input for different tasks such as simulating erosion, generating elevation models, and completing missing areas. Finally, the architecture presented in [12] uses water maps as input to generate synthetic digital elevation models and land surface imagery of river deltas fitting three different cGANs. The first one uses a water map as input and generates its elevation model.…”

Section: Related Workmentioning

confidence: 99%

“…The third module uses the method proposed in [12] to generate digital elevation models (DEMs) and realistic delta surface images. The cGANs approach proposes to use as input either a user-drawn sketch or a real-world water map.…”

Section: The Elevation Model and Surface Image Modulementioning

confidence: 99%

“…However, this paper introduces an automatic process for generating original river deltas without manual intervention using the water maps from our proposed first two modules. The generated water maps are used as input for the original cGANs, which were trained and validated using the DRCA2020 dataset, publicly available in https://github.com/DRCA2020/Tropical-Rainforestand-Monsoon [12]. Figure 12 shows the generation pipeline presented in [12].…”

Section: The Elevation Model and Surface Image Modulementioning

confidence: 99%

“…The generated water maps are used as input for the original cGANs, which were trained and validated using the DRCA2020 dataset, publicly available in https://github.com/DRCA2020/Tropical-Rainforestand-Monsoon [12]. Figure 12 shows the generation pipeline presented in [12].…”

Section: The Elevation Model and Surface Image Modulementioning

confidence: 99%

“…The river delta structure is not enough to create a realistic landscape on its own; that is why we propose the integration of generative techniques such as conditional generative adversarial networks (cGANs) and L-systems. We incorporate the approach in [12] that uses a triplet of cGAN models to Orinoco, (c) Grijalva, and (d) Krishna. These water maps were obtained from the European Space Agency through its Global Surface Water platform [14].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Modular Generative Approach for Realistic River Deltas: When L-Systems and cGANs Meet

2022

Self Cite

View full text Add to dashboard Cite

Procedural terrain generation aims to create topographically coherent landscapes with realistic terrain features. Realistic landscapes of our blue planet are not complete without river deltas; however, there is an insufficient advancement in the generation of landscapes with this terrain feature. Therefore, this paper presents a modular approach to generate landscapes focused on the river deltas features. The modular proposal initially creates skeletons of deltas using a stochastic L-system grammar; we include the guidelines for the rules design. In the first module, we propose three L-systems that automatically create delta skeletons using these guidelines. The second module constructs the coastline and the sedimentary lands for the delta skeleton. Finally, the third module uses conditional generative adversarial networks (cGANs) to create the corresponding digital elevation models (DEMs) and land surface images. The evaluation of our proposal includes visual comparisons, and image quality metrics: the Frechet Inception Distance (FID), and the Naturalness Image Quality Evaluator (NIQE). The proposed modular integration generates realistic deltas with enough variability to outperform related work.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: The Elevation Model and Surface Image Modulementioning

confidence: 99%