Experiments in transform-based range image compression

Range images (depth maps) are seeing increased usage in a variety of application areas including entertainment, industrial automation, inspection, remote sensing, and military tactical planning. As the corpus of range imagery increases in size and the need to communicate such images over fixed-bandwidth channels increases, the compression of range data deserves investigation. Since the geometry encoded by range sensors is inherently "low-bandwidth", transform-based techniques seem appropriate for investigation in this context. This paper reports on experiments with a popular zerotree-based image codec (the SPIHT algorithm developed by Said and Pearlman) and its application to the compression of range imagery. Experiments suggest that compression rates of 1 bit/pixel and below are achievable with minimal impact on fidelity.