ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F25%3A00388523" target="_blank" >RIV/68407700:21730/25:00388523 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/CVPR52734.2025.02555" target="_blank" >https://doi.org/10.1109/CVPR52734.2025.02555</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52734.2025.02555" target="_blank" >10.1109/CVPR52734.2025.02555</a>

Result language

angličtina

Original language name

ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions

Original language description

The goal of this work is to generate step-by-step visual in structions in the form of a sequence of images, given an in put 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 in struction 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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

R - Projekt Ramcoveho programu EK

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3315-4364-8

ISSN

1063-6919

e-ISSN

2575-7075

Number of pages

11

Pages from-to

27435-27445

Publisher name

IEEE Computer Society

Place of publication

Los Alamitos

Event location

Nashville

Event date

Jun 11, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001601181100317