Before exploring and analyzing the corpus chosen for the representation of atmospheres, a simple example will be observed to measure the difficulty of the game of the representation of atmospheres in the project. This example is that of the choice that a designer could have between the strip window and the vertical window of the Renaissance type. This example has already been mentioned in the previous chapter as representative of the gap that can occur between an architectural discourse, the realization and the perception of the users. It seemed interesting to us at the beginning of the discussion on figuration to show that representation is a complex act passing through words and drawing.
A novel 3D generation method is introduced, enabling versatile and high-quality 3D asset creation. At its core is a unified Structured LATent (SLAT) representation, which supports decoding into multiple output formats, including Radiance Fields, 3D Gaussians, and meshes. This is achieved by combining a sparsely-populated 3D grid with dense multiview visual features extracted from a robust vision foundation model, effectively capturing both structural (geometry) and textural (appearance) information while preserving decoding flexibility.
Structured 3D Latents for Scalable and Versatile 3D Generation (https://trellis3d.github.io/) 
