Forward Image Mapping

Baoquan Chen, Frank Dachille, Arie Kaufman

Abstract

We present a new forward image mapping algorithm, which speeds up perspective warping -- as in texture mapping. It processes the source image in a special scanline order instead of the normal raster scanline order. This special scanline has the property of preserving parallelism when projecting to the target image. The algorithm reduces the complexity of perspective-correct image warping by eliminating the division per pixel and replacing it with a division per scanline. The method also corrects the perspective distortion in Gouraud shading with negligible overhead. Furthermore, the special scanline order is suitable for antialiasing using a more accurate antialiasing conic filter, with minimum additional cost. The algorithm is highlighted by incremental calculations and optimized memory bandwidth by reading each source pixel only once, suggesting a potential hardware implementation.

Electronic Paper

[ gziped PS ]
[ PDF ]

Results

EWA (elliptical weighted average) with filter radius of 1.5 pixels (6.7 seconds). A small kernel leads to some aliasing. "Higher Quality EWA" with filter radius of 2.5 pixels (22.0 seconds). A larger kernel leads to blurring. Our method with filter radius of 1.5 pixels (2.2 seconds). With the same kernel size our method offers better antialiasing, less blurring, and greater efficiency

You can find more about my research here.