SYSTEMS AND METHODS FOR DECODING LIGHT FIELD IMAGE FILES HAVING DEPTH AND CONFIDENCE MAPS

摘要

Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map to create a rendered image.

主权项

1. A system for rendering an image using a light field image file, the system comprising:
a processor; and memory containing a rendering application and a light field image file; wherein the light field image file comprises:
an encoded image; andmetadata describing the encoded image stored within an application marker segment within the light field image file; wherein the metadata comprises:
a depth map that specifies depths for pixels in the encoded image; anda confidence map for the depth map, where the confidence map indicates the reliability of the depth values provided for pixels by the depth map; and wherein the rendering application directs the processor to render an image by applying post processing to the encoded image using metadata contained within the light field image by:
locating the encoded image within the light field image file by locating a start of image marker within the light field image file;decoding the encoded image;locating the metadata within the light field image file; andprocessing the decoded image by modifying the pixels of the decoded image based on the depths of the pixels indicated within the depth map and the reliability of the depth values indicated within the confidence map to create a rendered image by applying a depth based effect to the pixels of the decoded image.