ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
This addresses the challenge of producing multi-step visual guides for complex tasks in specific environments, which is incremental as it builds on existing video generation and instruction-following methods.
The authors tackled the problem of generating step-by-step visual instructions as image sequences from a scene image and textual instructions, and they achieved state-of-the-art results across accuracy dimensions by creating a large dataset and training a video diffusion model.
The goal of this work is to generate step-by-step visual instructions in the form of a sequence of images, given an input image that provides the scene context and the sequence of textual instructions. This is a challenging problem as it requires generating multi-step image sequences to achieve a complex goal while being grounded in a specific environment. Part of the challenge stems from the lack of large-scale training data for this problem. The contribution of this work is thus three-fold. First, we introduce an automatic approach for collecting large step-by-step visual instruction training data from instructional videos. We apply this approach to one million videos and create a large-scale, high-quality dataset of 0.6M sequences of image-text pairs. Second, we develop and train ShowHowTo, a video diffusion model capable of generating step-by-step visual instructions consistent with the provided input image. Third, we evaluate the generated image sequences across three dimensions of accuracy (step, scene, and task) and show our model achieves state-of-the-art results on all of them. Our code, dataset, and trained models are publicly available.