# 1 **Data driven creation** difficulty Hard to combine pieces, no understanding of visual realism. Different distribution on different sources. The richness of real world. (complex) 2D projection on 3d world. Computer graphics * great creative possibilities * easy to manipulate objects/viewpoint * tremendous expertise and effot to obtain realism. Photography * Instantly realistic * easy to acquire * hard to manipulate objects/viewpoint. Want realism, manipulation and ease of capture. Goal: Help everyone create visual context easily. Teach machines to create realistic content. today: pretty real. data-driven graphics. Ingredients for success today: 1. big compute (gpus) 2. big models (dnns) 3. big data Highlights: image to image translation - pix2pix. (GANs) input can be translated into other view. Style transfer -> image + styleize it by taking a reference image. View interprolation ( change view) Text-based image editing. Diffusion Models. Create photorealistic scenes. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://tianyi0216.gitbook.io/blog/course_notes/cs-839-notes/1.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.