Nowadays, various AI image generation software is being developed, but basically they generate 2D images. A Singapore scientific research team recently announced that it is developing an artificial intelligence system that directly produces 3DVR images from text. If the project is completed, it will be used for the future. Drawing, film, animation and even games and other fields have caused a huge impact and influence.
• The research team at Nanyang Technological University in Singapore recently published a paper titled “Text2Light: Zero-Shot Text-Driven HDR Panorama Generation”, talking about the planning of this artificial intelligence project, which has attracted industry attention.
• With the current technical level of the AI industry, it is unrealistic to directly generate 4K-level HDR3D images via AI. However, this document describes how to implement the plan. First, the first phase of the AI needs to generate a 360 degree frame of low resolution LDR, then the second phase updates the results of the first phase to the HDR level and the search is currently active.
Further reading:
