Infinite details: A cartography-informed parametric method for constructing realistic 3D natural scenes

Realistic 3D scenes enhance spatial comprehension and support decision-making by creating intuitive and immersive representations of the physical world. However, achieving realism in natural scenes is challenging because of the complexity of microscale details influenced by natural disturbance events such as weathering, aging, and decay. This study introduces a cartography-informed parametric method for constructing 3D natural scenes with fine-scale details, including three components: a semantic tree, a spatial layout, and a model placement. The method simultaneously considers global entities and local details, where the generation of the latter is spatially constrained by the context of the former. Experiments are conducted across five natural scenes, and two types of user studies are carried out to evaluate visual perception. The results demonstrate the adaptability and effectiveness of the proposed method in scenes comprising various types of entities and details. Compared with scenes without details, scenes containing details exhibit superior visual realism, as evidenced by an average user rating scores of 3.51 versus 2.78 and a user selection count of 5.12 versus 0.88. This work provides a new methodological perspective on natural scene modeling and expands upon potential interdisciplinary applications that span dynamics and aesthetics.