Example-Based SuperResolution

Example-Based SuperResolution - Image-Based Modeling,...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
P olygon-based representations of 3D objects offer resolution independence over a wide range of scales. With this approach, object boundaries remain sharp when we zoom in on an object until very close range, where faceting appears due to finite polygon size (see Figure 1). However, constructing polygon models for complex, real-world objects can be difficult. Image- based rendering (IBR), a comple- mentary approach for representing and rendering objects, uses cameras to obtain rich models directly from real-world data. Unfortunately, these representations no longer have resolution independence. When we enlarge a bitmapped image, we get a blurry result. Figure 2 shows the problem for an IBR ver- sion of a teapot image, rich with real-world detail. Standard pixel interpolation methods, such as pixel replication (Figures 2b and 2c) and cubic-spline interpolation (Fig- ures 2d and 2e), introduce artifacts or blur edges. For images enlarged three octaves (fac- tors of two) such as these, sharpening the interpolated result has little useful effect (Figures 2f and 2g). We call methods for achieving high-resolution enlargements of pixel-based images super-resolution algorithms. Many applications in graphics or image pro- cessing could benefit from such resolution indepen- dence, including IBR, texture mapping, enlarging consumer photographs, and converting NTSC video content to high-de±nition television. We built on anoth- er training-based super-resolution algorithm 1 and devel- oped a faster and simpler algorithm for one-pass super-resolution. (The one-pass, example-based algo- rithm gives the enlargements in Figures 2h and 2i.) Our algorithm requires only a nearest-neighbor search in the training set for a vector derived from each patch of local image data. This one-pass super-resolution algorithm is a step toward achieving resolution independence in image-based representations. We don’t expect perfect resolution independence—even the polygon represen- tation doesn’t have that—but increasing the resolution independence of pixel-based representations is an important task for IBR. Example-based approaches Super-resolution relates to image interpolation—how should we interpolate between the digital samples of a photograph? Researchers have long studied this prob- lem, although only recently with machine learning or sampling approaches. (See the “Related Approaches” sidebar for more details.) Three complimentary ways exist for increasing an image’s apparent resolution: 0272-1716/02/$17.00 © 2002 IEEE Image-Based Modeling, Rendering, and Lighting 56 March/April 2002 To address the lack of resolution independence in most models, we developed a fast and simple one-pass, training-based super- resolution algorithm for creating plausible high- frequency details in zoomed images.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 04/22/2010 for the course MI IP taught by Professor Vladbalan during the Spring '10 term at Universidad del Rosario.

Page1 / 10

Example-Based SuperResolution - Image-Based Modeling,...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online