# LaxMotion: Rethinking Supervision Granularity for 3D Human Motion Generation

arXiv: https://arxiv.org/abs/2511.11368 · HTML: https://mlsanity.com/paper/2511.11368/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Builds on 38 of its 42 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 30 of 38)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts](https://mlsanity.com/paper/2207.01696/) (2022)
- [The KIT Motion-Language Dataset](https://mlsanity.com/paper/1607.03827/) (2016)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows](https://mlsanity.com/paper/2003.10350/) (2020)
- [RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1902.09868/) (2019)
- [Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression](https://mlsanity.com/paper/2411.16575/) (2024)
- [In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations](https://mlsanity.com/paper/1904.03289/) (2019)
- [OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers](https://mlsanity.com/paper/2312.08985/) (2023)
- [Can 3D Pose be Learned from 2D Projections Alone?](https://mlsanity.com/paper/1808.07182/) (2018)
- [Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis](https://mlsanity.com/paper/2004.04400/) (2020)
- [MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion](https://mlsanity.com/paper/2310.14729/) (2023)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)

## Abstract (arXiv)

Recent 3D human motion generation models demonstrate remarkable reconstruction accuracy yet struggle to generalize beyond training distributions. This limitation arises partly from the use of precise 3D supervision, which encourages models to fit fixed coordinate patterns instead of learning the essential 3D structure and motion semantic cues required for robust generalization. To overcome this limitation, we propose LaxMotion, a framework that synthesizes realistic 3D motions without direct 3D pose supervision. Instead of regressing toward exact coordinates, LaxMotion learns 3D motion as a consistent explanation of global trajectories and monocular 2D kinematic cues. We introduce a structured motion factorization together with a reformulated training paradigm under relaxed observability. This design is further supported by relaxed regularization objectives that enforce view consistent alignment, orientation coherence, and structural stability. Under this relaxed supervision paradigm, LaxMotion generates diverse, temporally coherent, and semantically aligned 3D motions, achieving performance comparable to or surpassing fully 3D supervised methods. These results indicate that shifting supervision from exact coordinate matching to structural consistency promotes stronger reasoning and improved generalization, offering a scalable and data efficient paradigm for 3D motion generation.