When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability
This addresses a practical issue for non-expert users in image generation by enhancing controllability with inexplicit masks, though it is incremental as it builds on existing ControlNet methods.
The paper tackles the problem of ControlNet generating artifacts from noisy user-provided masks by proposing a Shape-aware ControlNet with a deterioration estimator and shape-prior modulation block, which improves robustness and reduces unwanted artifacts in diverse conditions.
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 is devised. The deterioration estimator assesses the deterioration factor of the provided masks. Then this factor is utilized in the modulation block to adaptively modulate the model's contour-following ability, which helps it dismiss the noise part in the inexplicit masks. Extensive experiments prove its effectiveness in encouraging ControlNet to interpret inaccurate spatial conditions robustly rather than blindly following the given contours, suitable for diverse kinds of conditions. We showcase application scenarios like modifying shape priors and composable shape-controllable generation. Codes are available at github.