MetadataShow full item record
This thesis proposes a method for changing the lighting in some types of images. The method requires only a single input image, either a studio photograph or a synthetic image, consisting of several simple objects placed on a uniformly coloured background. Based on 2D information (contours, shadows, specular areas) extracted from the input image, the method reconstructs a 3D model of the original lighting and and 2.5D models of objects in the image. It then modifies the appearance of shading and shadows to achieve relighting. It can produce visually satisfactory results without a full 3D description of the scene geometry, and requires minimal user assistance. While developing this method, the importance of different cues for understanding 3D geometry, such as contours or shadows, were considered. Constraints like symmetry that help determine surface shapes were also explored. The method has potential application in improving the appearance of existing photographs. It can also be used in image compositing to achieve consistent lighting.
Cite this version of the work
Jingyuan Huang (2010). Image-Based Relighting. UWSpace. http://hdl.handle.net/10012/5083