Saved in:
Bibliographic Details
Main Authors: Wen, Di, Zhong, Zeyun, Schneider, David, Zaremski, Manuel, Kunzmann, Linus, Shi, Yitian, Liu, Ruiping, Chen, Yufan, Zheng, Junwei, Li, Jiahang, Hemmerich, Jonas, Tong, Qiyi, Grauberger, Patric, Ajoudani, Arash, Paudel, Danda Pani, Matthiesen, Sven, Deml, Barbara, Beyerer, Jürgen, Van Gool, Luc, Stiefelhagen, Rainer, Peng, Kunyu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10409
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915933324312576
author Wen, Di
Zhong, Zeyun
Schneider, David
Zaremski, Manuel
Kunzmann, Linus
Shi, Yitian
Liu, Ruiping
Chen, Yufan
Zheng, Junwei
Li, Jiahang
Hemmerich, Jonas
Tong, Qiyi
Grauberger, Patric
Ajoudani, Arash
Paudel, Danda Pani
Matthiesen, Sven
Deml, Barbara
Beyerer, Jürgen
Van Gool, Luc
Stiefelhagen, Rainer
Peng, Kunyu
author_facet Wen, Di
Zhong, Zeyun
Schneider, David
Zaremski, Manuel
Kunzmann, Linus
Shi, Yitian
Liu, Ruiping
Chen, Yufan
Zheng, Junwei
Li, Jiahang
Hemmerich, Jonas
Tong, Qiyi
Grauberger, Patric
Ajoudani, Arash
Paudel, Danda Pani
Matthiesen, Sven
Deml, Barbara
Beyerer, Jürgen
Van Gool, Luc
Stiefelhagen, Rainer
Peng, Kunyu
contents We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our knowledge, IMPACT is the first real industrial assembly benchmark that jointly provides synchronized ego-exo RGB-D capture, decoupled bimanual annotation, compliance-aware state tracking, and explicit anomaly--recovery supervision within a single real industrial workflow. It comprises 112 trials from 13 participants totaling 39.5 hours, with multi-route execution governed by a partial-order prerequisite graph, a six-category anomaly taxonomy, and operator cognitive load measured via NASA-TLX. The annotation hierarchy links hand-specific atomic actions to coarse procedural steps, component assembly states, and per-hand compliance phases, with synchronized null spans across views to decouple perceptual limitations from algorithmic failure. Systematic baselines reveal fundamental limitations that remain invisible to single-task benchmarks, particularly under realistic deployment conditions that involve incomplete observations, flexible execution paths, and corrective behavior. The full dataset, annotations, and evaluation code are available at https://github.com/Kratos-Wen/IMPACT.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10409
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly
Wen, Di
Zhong, Zeyun
Schneider, David
Zaremski, Manuel
Kunzmann, Linus
Shi, Yitian
Liu, Ruiping
Chen, Yufan
Zheng, Junwei
Li, Jiahang
Hemmerich, Jonas
Tong, Qiyi
Grauberger, Patric
Ajoudani, Arash
Paudel, Danda Pani
Matthiesen, Sven
Deml, Barbara
Beyerer, Jürgen
Van Gool, Luc
Stiefelhagen, Rainer
Peng, Kunyu
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our knowledge, IMPACT is the first real industrial assembly benchmark that jointly provides synchronized ego-exo RGB-D capture, decoupled bimanual annotation, compliance-aware state tracking, and explicit anomaly--recovery supervision within a single real industrial workflow. It comprises 112 trials from 13 participants totaling 39.5 hours, with multi-route execution governed by a partial-order prerequisite graph, a six-category anomaly taxonomy, and operator cognitive load measured via NASA-TLX. The annotation hierarchy links hand-specific atomic actions to coarse procedural steps, component assembly states, and per-hand compliance phases, with synchronized null spans across views to decouple perceptual limitations from algorithmic failure. Systematic baselines reveal fundamental limitations that remain invisible to single-task benchmarks, particularly under realistic deployment conditions that involve incomplete observations, flexible execution paths, and corrective behavior. The full dataset, annotations, and evaluation code are available at https://github.com/Kratos-Wen/IMPACT.
title IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.10409