Abstract: In one embodiment, a computing system may access a first grayscale image and a second grayscale image. The system may generate a first color image and a second color image based on the first grayscale image and the second grayscale image, respectively. The system may generate affinity information based on the first grayscale image and the second grayscale image, the affinity information identifying relationships between pixels of the first grayscale image and pixels of the second grayscale image. The system may modify the color of the first color image and the second color image based on the affinity information. The system may generate a first visual output based on the modified first color image and a second visual output based on the modified second color image.

Abstract: A method for generating object and part detectors includes accessing a collection of training images. The collection of training images includes images annotated with an object label and images annotated with a respective part label for each of a plurality of parts of the object. Joint appearance-geometric embeddings for regions of a set of the training images are generated. At least one detector for the object and its parts is learnt using annotations of the training images and respective joint appearance-geometric embeddings, e.g., using multi-instance learning for generating parameters of scoring functions which are used to identify high scoring regions for learning the object and its parts. The detectors may be output or used to label regions of a new image with object and part labels.