Image Generation

Image generation (synthesis) is the task of generating new images from an existing dataset. Unconditional generation refers to generating samples unconditionally from the dataset, i.e., \(p(y)\); while conditional generation involves generating samples based on labels from the dataset, i.e., \(p(y|x)\). This section showcases the latest leaderboard for unconditional generation, while other types of image generation can be found in subtasks. Image generation holds significant application value in computer vision, being useful for data augmentation, artistic creation, and virtual reality, among other fields.