# PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation

arXiv: https://arxiv.org/abs/2603.22193 · HTML: https://mlsanity.com/paper/2603.22193/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 82 of its 94 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 30 of 82)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [VideoComposer: Compositional Video Synthesis with Motion Controllability](https://mlsanity.com/paper/2306.02018/) (2023)
- [CameraCtrl: Enabling Camera Control for Text-to-Video Generation](https://mlsanity.com/paper/2404.02101/) (2024)
- [HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction](https://mlsanity.com/paper/2203.01577/) (2022)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2](https://mlsanity.com/paper/2112.14683/) (2021)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies](https://mlsanity.com/paper/1801.01615/) (2018)
- [DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos](https://mlsanity.com/paper/2409.02095/) (2024)
- [Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control](https://mlsanity.com/paper/2501.03847/) (2025)
- [Grasping Field: Learning Implicit Representations for Human Grasps](https://mlsanity.com/paper/2008.04451/) (2020)
- [SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://mlsanity.com/paper/2311.16933/) (2023)
- [Hand-Object Contact Consistency Reasoning for Human Grasps Generation](https://mlsanity.com/paper/2104.03304/) (2021)
- [OakInk: A Large-scale Knowledge Repository for Understanding Hand-Object Interaction](https://mlsanity.com/paper/2203.15709/) (2022)
- [CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos](https://mlsanity.com/paper/2410.11831/) (2024)
- [IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions](https://mlsanity.com/paper/2212.07555/) (2022)
- [UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy](https://mlsanity.com/paper/2303.00938/) (2023)

## Built on by (most cited first, 3 of 3)

- [From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation](https://mlsanity.com/paper/2605.08712/) (2026)
- [Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer](https://mlsanity.com/paper/2607.28394/) (2026)
- [ConGraspXL: Controllable Constraint-Conditioned Dexterous Grasping Motion Synthesis](https://mlsanity.com/paper/2609.16319/) (2026)

## Abstract (arXiv)

Hand-object interaction (HOI) reconstruction and synthesis are becoming central to embodied AI and AR/VR. Yet, despite rapid progress, existing HOI generation research remains fragmented across three disjoint tracks: (1) pose-only synthesis that predicts MANO trajectories without producing pixels; (2) single-image HOI generation that hallucinates appearance from masks or 2D cues but lacks dynamics; and (3) video generation methods that require both the entire pose sequence and the ground-truth first frame as inputs, preventing true sim-to-real deployment. Inspired by the philosophy of Joo et al. (2018), we think that HOI generation requires a unified engine that brings together pose, appearance, and motion within one coherent framework. Thus we introduce PAM: a Pose-Appearance-Motion Engine for controllable HOI video generation. The performance of our engine is validated by: (1) On DexYCB, we obtain an FVD of 29.13 (vs. 38.83 for InterDyn), and MPJPE of 19.37 mm (vs. 30.05 mm for CosHand), while generating higher-resolution 480x720 videos compared to 256x256 and 256x384 baselines. (2) On OAKINK2, our full multi-condition model improves FVD from 68.76 to 46.31. (3) An ablation over input conditions on DexYCB shows that combining depth, segmentation, and keypoints consistently yields the best results. (4) For a downstream hand pose estimation task using SimpleHand, augmenting training with 3,400 synthetic videos (207k frames) allows a model trained on only 50% of the real data plus our synthetic data to match the 100% real baseline.