Paper page - H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models

Source: https://huggingface.co/papers/2608.13049

Abstract

H2R-Bench evaluates video generation models on transforming human manipulation videos into robot-centric demonstrations across embodiment constraints and interaction fidelity.

Large-scale manipulation data is essential for robot learning, yet collecting robot demonstrations remains expensive and difficult to scale. Meanwhile, abundant egocentric human manipulation videos provide rich behavioral experiences, but transferring them across embodiments remains challenging due to differences between human hands and robotic end-effectors. Recent advances invideo world modelsoffer a promising pathway to synthesize robot-centric manipulation videos from human observations, while theircross-embodiment transfercapability remains largely unexplored. Therefore, we introduce H2R-Bench, a benchmark for evaluating cross-embodimenthuman-to-robot manipulationvideo generation, where models transform egocentric human demonstrations into robot manipulation videos under specified embodiments. Each benchmark instance contains a human demonstration video, targetembodiment constraints, and source-grounded annotations covering task goals,action events,functional contacts, and object responses. H2R-Bench evaluates generated videos through five dimensions, includinggoal-state completion, action-event completion,functional contacttransfer, embodiment correctness, and general video quality. We benchmark eleven state-of-the-art video generation models across six manipulation families and two robot embodiments. Our evaluation reveals that currentvideo world modelsremain limited inhuman-to-robot manipulationtransfer: even leading models often fail in embodiment consistency, functional interaction, and task execution. H2R-Bench provides a systematic diagnostic framework for evaluating whethervideo world modelscan bridge the human-to-robot embodiment gap and convert human manipulation observations into robot-centric training resources.

View arXiv pageView PDFProject pageGitHub0Add to collection

Get this paper in your agent:

hf papers read 2608\.13049

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2608.13049 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2608.13049 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2608.13049 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.