This AI Paper Proposes A Latent Diffusion Model For 3D (LDM3D) That Generates Both Image And Depth Map Data From A Given Text Prompt


GPT-4: Researchers have developed a Latent Diffusion Model for 3D (LDM3D) that generates high-fidelity RGB images and depth maps from text prompts, enabling immersive 360° experiences. Built upon Stable Diffusion v1.4, LDM3D was refined using a dataset of 4 million tuples. The team also created DepthFusion, an application that calculates 360° projections using TouchDesigner. This technology has the potential to revolutionize industries such as gaming, entertainment, design, and architecture by transforming how people interact with digital content.
Read more at MarkTechPost…