# Articulated Kinematics Distillation from Video Diffusion Models

arXiv: https://arxiv.org/abs/2504.01204 · HTML: https://mlsanity.com/paper/2504.01204/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 54 of its 67 references that are in the map.
- First posted on arXiv 1 Apr 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 54)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Text-To-4D Dynamic Scene Generation](https://mlsanity.com/paper/2301.11280/) (2023)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [DreamGaussian4D: Generative 4D Gaussian Splatting](https://mlsanity.com/paper/2312.17142/) (2023)
- [PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation](https://mlsanity.com/paper/2404.13026/) (2024)
- [4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling](https://mlsanity.com/paper/2311.17984/) (2023)
- [SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting](https://mlsanity.com/paper/2403.05087/) (2024)
- [Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models](https://mlsanity.com/paper/2312.13763/) (2023)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [Monocular Total Capture: Posing Face, Body, and Hands in the Wild](https://mlsanity.com/paper/1812.01598/) (2018)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [L4GM: Large 4D Gaussian Reconstruction Model](https://mlsanity.com/paper/2406.10324/) (2024)

## Built on by (most cited first, 13 of 13)

- [Puppeteer: Rig and Animate Your 3D Models](https://mlsanity.com/paper/2508.10898/) (2025)
- [AnimaMimic: Imitating 3D Animation from Video Priors](https://mlsanity.com/paper/2512.14133/) (2025)
- [Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference](https://mlsanity.com/paper/2603.01594/) (2026)
- [SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting](https://mlsanity.com/paper/2601.00285/) (2026)
- [Ani3DHuman: Photorealistic 3D Human Animation with Self-guided Stochastic Sampling](https://mlsanity.com/paper/2602.19089/) (2026)
- [Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization](https://mlsanity.com/paper/2605.28394/) (2026)
- [Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories](https://mlsanity.com/paper/2606.25344/) (2026)
- [ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors](https://mlsanity.com/paper/2603.04338/) (2026)
- [PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions](https://mlsanity.com/paper/2605.30268/) (2026)
- [Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text](https://mlsanity.com/paper/2606.05162/) (2026)
- [AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects](https://mlsanity.com/paper/2606.10988/) (2026)
- [G-Skin: Learning to Bind 3D Gaussians with Generative Visual Priors](https://mlsanity.com/paper/2608.01726/) (2026)
- [Strike a Chord! Modal Kinetic Typography](https://mlsanity.com/paper/2609.38325/) (2026)

## Abstract (arXiv)

We present Articulated Kinematics Distillation (AKD), a framework for generating high-fidelity character animations by merging the strengths of skeleton-based animation and modern generative models. AKD uses a skeleton-based representation for rigged 3D assets, drastically reducing the Degrees of Freedom (DoFs) by focusing on joint-level control, which allows for efficient, consistent motion synthesis. Through Score Distillation Sampling (SDS) with pre-trained video diffusion models, AKD distills complex, articulated motions while maintaining structural integrity, overcoming challenges faced by 4D neural deformation fields in preserving shape consistency. This approach is naturally compatible with physics-based simulation, ensuring physically plausible interactions. Experiments show that AKD achieves superior 3D consistency and motion quality compared with existing works on text-to-4D generation. Project page: https://research.nvidia.com/labs/dir/akd/