When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability

arXiv:2403.00467v1 Announce Type: new
Abstract: ControlNet excels at creating content that closely matches precise contours in user-provided masks. However, when these masks contain noise, as a frequent occurrence with non-expert users, the output would include unwanted artifacts. This paper first highlights the crucial role of controlling the impact of these inexplicit masks with diverse deterioration levels through in-depth analysis. Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block …

abstract arxiv case case study contour controlnet cs.cv expert highlights masks noise paper role study type