HumanScore: Benchmarking Human Motions in Generated Videos

• URL: http://arxiv.org/abs/2604.20157v1
• Date: Wed, 22 Apr 2026 03:51:19 GMT
• Title: HumanScore: Benchmarking Human Motions in Generated Videos
• Abstract summary: We present HumanScore, a framework to evaluate the quality of human motions in AI-generated videos.<n>HumanScore defines six interpretable metrics spanning kinematic plausibility, temporal stability, and biomechanical consistency.<n>Our analysis reveals consistent gaps between perceptual plausibility and motion biomechanical fidelity.
• Score: 16.29197573772623
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in model architectures, compute, and data scale have driven rapid progress in video generation, producing increasingly realistic content. Yet, no prior method systematically measures how faithfully these systems render human bodies and motion dynamics. In this paper, we present HumanScore, a systematic framework to evaluate the quality of human motions in AI-generated videos. HumanScore defines six interpretable metrics spanning kinematic plausibility, temporal stability, and biomechanical consistency, enabling fine-grained diagnosis beyond visual realism alone. Through carefully designed prompts, we elicit a diverse set of movements at varying intensities and evaluate videos generated by thirteen state-of-the-art models. Our analysis reveals consistent gaps between perceptual plausibility and motion biomechanical fidelity, identifies recurrent failure modes (e.g., temporal jitter, anatomically implausible poses, and motion drift), and produces robust model rankings from quantitative and physically meaningful criteria.

Related papers

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models [66.77745044586173]
  GAUGE is a real-world-grounded diagnostic benchmark for evaluating how numerical simulators and generative video world models reproduce or deviate from real-world physics.<n>We benchmark Isaac Sim, Genesis, and Newton on 14 task families using generalized trajectory errors, and evaluate 6 image-to-video models on 5 rigid-body tasks.<n>Our results reveal no uniformly faithful physics engine, with the largest discrepancies arising in impulsive contact, rapid textile motion, and volumetric deformation.
  arXiv  Detail & Related papers  (2026-08-06T12:19:38Z)
• BioHuman: Learning Biomechanical Human Representations from Video [11.653644899302542]
  We introduce a simulation-based framework for estimating muscle activations from existing motion capture datasets.<n>We propose BioHuman, an end-to-end model that takes monocular video as input and jointly predicts human motion and muscle activations.
  arXiv  Detail & Related papers  (2026-05-14T12:36:53Z)
• Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoning [77.34919361116037]
  Video generation models are increasingly used as world simulators for storytelling, simulation, and embodied AI.<n>Existing evaluations largely rely on automated metrics or coarse human judgments such as preferences or rubric-based checks.<n>We introduce Physion-Eval, a benchmark of expert human reasoning for diagnosing physical realism failures in videos generated by five state-of-the-art models.
  arXiv  Detail & Related papers  (2026-03-20T03:25:41Z)
• MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction [54.36564144414704]
  MeshMimic is an innovative framework that bridges 3D scene reconstruction and embodied intelligence to enable humanoid robots to learn coupled "motion-terrain" interactions directly from video.<n>By leveraging state-of-the-art 3D vision models, our framework precisely segments and reconstructs both human trajectories and the underlying 3D geometry of terrains and objects.
  arXiv  Detail & Related papers  (2026-02-17T17:09:45Z)
• Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos [4.872114804382539]
  We introduce a novel evaluation metric derived from a learned latent space of real-world human actions.<n>Our method first captures the nuances, constraints, and temporal smoothness of real-world motion by fusing appearance-agnostic human skeletal geometry features with appearance-based features.<n>Given a generated video, our metric quantifies its action quality by measuring the distance between its underlying representations and this learned real-world action distribution.
  arXiv  Detail & Related papers  (2025-12-01T15:36:33Z)
• Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and Estimation [21.750804738752105]
  We propose BioVAE, a biomechanics-aware framework with three core innovations.<n>We show that BioVAE achieves state-of-the-art performance on multiple benchmarks.
  arXiv  Detail & Related papers  (2025-03-08T10:22:36Z)
• Aligning Human Motion Generation with Human Perceptions [51.831338643012444]
  We propose a data-driven approach to bridge the gap by introducing a large-scale human perceptual evaluation dataset, MotionPercept, and a human motion critic model, MotionCritic.<n>Our critic model offers a more accurate metric for assessing motion quality and could be readily integrated into the motion generation pipeline.
  arXiv  Detail & Related papers  (2024-07-02T14:01:59Z)
• 3D Kinematics Estimation from Video with a Biomechanical Model and Synthetic Training Data [4.130944152992895]
  We propose a novel biomechanics-aware network that directly outputs 3D kinematics from two input views. Our experiments demonstrate that the proposed approach, only trained on synthetic data, outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-02-20T17:33:40Z)
• Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening [59.88594294676711]
  Modern deep learning based motion synthesis approaches barely consider the physical plausibility of synthesized motions. We propose a system Skeleton2Humanoid'' which performs physics-oriented motion correction at test time. Experiments on the challenging LaFAN1 dataset show our system can outperform prior methods significantly in terms of both physical plausibility and accuracy.
  arXiv  Detail & Related papers  (2022-10-09T16:15:34Z)
• Learning Local Recurrent Models for Human Mesh Recovery [50.85467243778406]
  We present a new method for video mesh recovery that divides the human mesh into several local parts following the standard skeletal model. We then model the dynamics of each local part with separate recurrent models, with each model conditioned appropriately based on the known kinematic structure of the human body. This results in a structure-informed local recurrent learning architecture that can be trained in an end-to-end fashion with available annotations.
  arXiv  Detail & Related papers  (2021-07-27T14:30:33Z)
• Dynamic Future Net: Diversified Human Motion Generation [31.987602940970888]
  Human motion modelling is crucial in many areas such as computer graphics, vision and virtual reality. We present Dynamic Future Net, a new deep learning model where we explicitly focuses on the intrinsic motionity of human motion dynamics. Our model can generate a large number of high-quality motions with arbitrary duration, and visuallyincing variations in both space and time.
  arXiv  Detail & Related papers  (2020-08-25T02:31:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.