# Aligning Human Motion Generation with Human Perceptions

arXiv: https://arxiv.org/abs/2407.02272 · HTML: https://mlsanity.com/paper/2407.02272/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 68 references that are in the map.
- First posted on arXiv 2 Jul 2024.

## Builds on (most cited first, 30 of 34)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment](https://mlsanity.com/paper/2304.06767/) (2023)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [Aligning Text-to-Image Models using Human Feedback](https://mlsanity.com/paper/2302.12192/) (2023)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [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)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)
- [Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory](https://mlsanity.com/paper/2203.13055/) (2022)
- [Generating Holistic 3D Human Motion from Speech](https://mlsanity.com/paper/2212.04420/) (2022)
- [Rich Human Feedback for Text-to-Image Generation](https://mlsanity.com/paper/2312.10240/) (2023)
- [Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes](https://mlsanity.com/paper/2012.05522/) (2020)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [InstructVideo: Instructing Video Diffusion Models with Human Feedback](https://mlsanity.com/paper/2312.12490/) (2023)
- [Context-aware Human Motion Prediction](https://mlsanity.com/paper/1904.03419/) (2019)
- [Dance Revolution: Long-Term Dance Generation with Music via Curriculum Learning](https://mlsanity.com/paper/2006.06119/) (2020)
- [CIRCLE: Capture In Rich Contextual Environments](https://mlsanity.com/paper/2303.17912/) (2023)
- [PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting](https://mlsanity.com/paper/2210.10542/) (2022)
- [Inverse Preference Learning: Preference-based RL without a Reward Function](https://mlsanity.com/paper/2305.15363/) (2023)

## Built on by (most cited first, 16 of 16)

- [The Quest for Generalizable Motion Generation: Data, Model, and Evaluation](https://mlsanity.com/paper/2510.26794/) (2025)
- [Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding](https://mlsanity.com/paper/2506.10353/) (2025)
- [IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation](https://mlsanity.com/paper/2512.10730/) (2025)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation](https://mlsanity.com/paper/2602.07967/) (2026)
- [PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation](https://mlsanity.com/paper/2605.14269/) (2026)
- [U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation](https://mlsanity.com/paper/2602.23739/) (2026)
- [Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and Estimation](https://mlsanity.com/paper/2503.06151/) (2025)
- [Quality assessment of 3D human animation: Subjective and objective evaluation](https://mlsanity.com/paper/2505.23301/) (2025)
- [Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward](https://mlsanity.com/paper/2506.03191/) (2025)
- [HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark](https://mlsanity.com/paper/2608.13555/) (2026)
- [FMReward: Aligning and Evaluating Audio-Driven 3D Facial Animation with Human Preferences](https://mlsanity.com/paper/2608.15296/) (2026)
- [MoRL: Reinforced Reasoning for Unified Motion Understanding and Generation](https://mlsanity.com/paper/2602.14534/) (2026)
- [Towards Highly-Constrained Human Motion Generation with Retrieval-Guided Diffusion Noise Optimization](https://mlsanity.com/paper/2605.08054/) (2026)
- [MotionMERGE: A Multi-granular Framework for Human Motion Editing, Reasoning, Generation, and Explanation](https://mlsanity.com/paper/2605.18956/) (2026)
- [Multi-Modal Controlled Coherent Motion Generation](https://mlsanity.com/paper/2609.11439/) (2026)

## Abstract (arXiv)

Human motion generation is a critical task with a wide range of applications. Achieving high realism in generated motions requires naturalness, smoothness, and plausibility. Despite rapid advancements in the field, current generation methods often fall short of these goals. Furthermore, existing evaluation metrics typically rely on ground-truth-based errors, simple heuristics, or distribution distances, which do not align well with human perceptions of motion quality. In this work, we propose a data-driven approach to bridge this gap by introducing a large-scale human perceptual evaluation dataset, MotionPercept, and a human motion critic model, MotionCritic, that capture human perceptual preferences. Our critic model offers a more accurate metric for assessing motion quality and could be readily integrated into the motion generation pipeline to enhance generation quality. Extensive experiments demonstrate the effectiveness of our approach in both evaluating and improving the quality of generated human motions by aligning with human perceptions. Code and data are publicly available at https://motioncritic.github.io/.