Coherent Stylization of Stereoscopic Images via Depth Slicing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for stylizing stereoscopic images often result in inconsistencies between the left and right views due to independent manipulation of images, leading to issues like exaggerated stroke lengths and undesirable regions.
Innovation Solution
The method involves using disparity maps to segment stereo images into slices representing specific depth ranges, merging and stylizing these slices coherently, and reassembling them to maintain consistency between views, allowing for more freedom in stylization and the use of image edges to direct brush strokes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional techniques apply painting algorithms independently to each stereo image, then stylization can be applied to both views, but inconsistencies arise between the left and right views
Solution Approach 1:
The patent segments the stereo image into depth layers using a disparity map, dividing the image space into multiple depth-based slices. This segmentation allows independent processing of each layer while maintaining overall coherence between left and right views, resolving the inconsistency problem by ensuring stylization operates on coherent depth structures rather than independently on each view.
Solution Approach 2:
The patent introduces depth maps and disparity information as intermediary elements that mediate between the left and right stereo images. These intermediaries provide a common reference framework that guides consistent stylization across both views, acting as a mediator that ensures coherence while allowing creative freedom in the stylization process.
2Area of stationary object
If brush strokes are extended to cover more areas, then stylization coverage is improved, but strokes wander into undesirable regions and create inconsistencies
Solution Approach 1:
The patent applies different stylization parameters and brush stroke characteristics to different depth layers and regions. By analyzing local image features and depth information, the system adjusts stroke length, direction, and intensity locally rather than applying uniform parameters globally. This allows strokes to extend into areas that need coverage while preventing them from wandering into undesirable regions, as each region receives appropriately tailored stylization treatment.
Data Source
AI summary
Methods and apparatus for coherent manipulation and stylization of stereoscopic images. A stereo image manipulation method may use the disparity map for a stereo image pair to divide the left and right images into a set of slices, each of which is the portion of the images that correspond to a certain, small depth range. The method may merge the left and right slices for a depth into a single image. The method may then apply a stylization technique to each slice. The method may then extract the left and right portions of each stylized slice, and stack them together to create a coherent stylized stereo image. As an alternative to first extracting slices from a merged image and then applying a stylization technique to the slices, the method may first apply the stylization technique to the merged image and then extract slices from the stylized merged image.