Research into non-line-of-sight imaging problems has gained momentum in recent years motivated by intriguing prospective applications in e.g. medicine and autonomous driving. While transient image formation is well understood and there exist various reconstruction approaches for non-line-of-sight scenes that combine efficient forward renderers with optimization schemes, those approaches suffer from runtimes in the order of hours even for moderately sized scenes. Furthermore, the ill-posedness of the inverse problem often leads to instabilities in the optimization.Inspired by the latest advances in direct-line-of-sight inverse rendering that have led to stunning results for reconstructing scene geometry and appearance, we present a fast differentiable transient renderer that accelerates the inverse rendering runtime to minutes on consumer hardware, making it possible to apply inverse transient imaging on a wider range of tasks and in more time-critical scenarios. We demonstrate its effectiveness on a series of applications using various datasets and show that it can be used for self-supervised learning.

Workflow management is an area of increasing interest. Nonetheless there are only a few workflow systems which are actually used for supporting business processes in an industrial context. Most of these systems only deal with processes which create and manipulate unstructured pieces of information, like documents and images. Our workflow management approach, called the FUNSOFT net approach, additionally supports the management of structured pieces of information, called objects. In doing so, we use a repository which is used to store information about process models and about individual processes. This repository is particularly useful for processes dealing with highly structured information, such as software processes. We describe the experience in using such a repository. We point out which of these experiences may be useful for developers of other workflow management systems as well.