# Quality assessment of 3D human animation: Subjective and objective evaluation

arXiv: https://arxiv.org/abs/2505.23301 · HTML: https://mlsanity.com/paper/2505.23301/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 87 references that are in the map.
- First posted on arXiv 29 May 2025.

## Builds on (most cited first, 30 of 41)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes](https://mlsanity.com/paper/2104.03953/) (2021)
- [WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion](https://mlsanity.com/paper/2312.07531/) (2023)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [Neural Kinematic Networks for Unsupervised Motion Retargetting](https://mlsanity.com/paper/1804.05653/) (2018)
- [HumanNorm: Learning Normal Diffusion Model for High-quality and Realistic 3D Human Generation](https://mlsanity.com/paper/2310.01406/) (2023)
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://mlsanity.com/paper/2205.13713/) (2022)
- [Generating Smooth Pose Sequences for Diverse Human Motion Prediction](https://mlsanity.com/paper/2108.08422/) (2021)
- [COAP: Compositional Articulated Occupancy of People](https://mlsanity.com/paper/2204.06184/) (2022)
- [AvatarGen: A 3D Generative Model for Animatable Human Avatars](https://mlsanity.com/paper/2211.14589/) (2022)
- [Shift-tolerant Perceptual Similarity Metric](https://mlsanity.com/paper/2207.13686/) (2022)
- [Perceptual Video Quality Assessment: A Survey](https://mlsanity.com/paper/2402.03413/) (2024)
- [QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation](https://mlsanity.com/paper/2305.11094/) (2023)
- [Neural Pose Transfer by Spatially Adaptive Instance Normalization](https://mlsanity.com/paper/2003.07254/) (2020)
- [ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction](https://mlsanity.com/paper/2303.05938/) (2023)
- [Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding](https://mlsanity.com/paper/2208.00281/) (2022)
- [Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry](https://mlsanity.com/paper/2303.08658/) (2023)
- [M3D-VTON: A Monocular-to-3D Virtual Try-On Network](https://mlsanity.com/paper/2108.05126/) (2021)
- [An Unsupervised Information-Theoretic Perceptual Quality Metric](https://mlsanity.com/paper/2006.06752/) (2020)
- [A Simple Baseline for Efficient Hand Mesh Reconstruction](https://mlsanity.com/paper/2403.01813/) (2024)
- [Textured Mesh Quality Assessment: Large-Scale Dataset and Deep Learning-based Quality Metric](https://mlsanity.com/paper/2202.02397/) (2022)
- [FinePOSE: Fine-Grained Prompt-Driven 3D Human Pose Estimation via Diffusion Models](https://mlsanity.com/paper/2405.05216/) (2024)
- [What is the Best Automated Metric for Text to Motion Generation?](https://mlsanity.com/paper/2309.10248/) (2023)
- [Aligning Human Motion Generation with Human Perceptions](https://mlsanity.com/paper/2407.02272/) (2024)
- [H4D: Human 4D Modeling by Learning Neural Compositional Representation](https://mlsanity.com/paper/2203.01247/) (2022)

## Built on by (most cited first, 1 of 1)

- [Multi-Agent Reinforcement Learning via Agent-Specific Preference](https://mlsanity.com/paper/2608.08604/) (2026)

## Abstract (arXiv)

Virtual human animations have a wide range of applications in virtual and augmented reality. While automatic generation methods of animated virtual humans have been developed, assessing their quality remains challenging. Recently, approaches introducing task-oriented evaluation metrics have been proposed, leveraging neural network training. However, quality assessment measures for animated virtual humans that are not generated with parametric body models have yet to be developed. In this context, we introduce a first such quality assessment measure leveraging a novel data-driven framework. First, we generate a dataset of virtual human animations together with their corresponding subjective realism evaluation scores collected with a user study. Second, we use the resulting dataset to learn predicting perceptual evaluation scores. Results indicate that training a linear regressor on our dataset results in a correlation of 90%, which outperforms a state of the art deep learning baseline.