# Cascaded Diffusion Framework for Probabilistic Coarse-to-Fine Hand Pose Estimation

arXiv: https://arxiv.org/abs/2510.00527 · HTML: https://mlsanity.com/paper/2510.00527/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 66 of its 79 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 66)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Cascaded Diffusion Models for High Fidelity Image Generation](https://mlsanity.com/paper/2106.15282/) (2021)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://mlsanity.com/paper/2311.04145/) (2023)
- [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](https://mlsanity.com/paper/2104.04631/) (2021)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.03713/) (2020)
- [FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images](https://mlsanity.com/paper/1909.04349/) (2019)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose](https://mlsanity.com/paper/2008.09047/) (2020)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [3D Hand Shape and Pose from Images in the Wild](https://mlsanity.com/paper/1902.03451/) (2019)
- [3D Hand Shape and Pose Estimation from a Single RGB Image](https://mlsanity.com/paper/1903.00812/) (2019)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild](https://mlsanity.com/paper/2004.01946/) (2020)
- [Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time](https://mlsanity.com/paper/2106.05266/) (2021)
- [End-to-end Hand Mesh Recovery from a Monocular RGB Image](https://mlsanity.com/paper/1902.09305/) (2019)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation](https://mlsanity.com/paper/2104.14639/) (2021)
- [Pushing the Envelope for RGB-based Dense 3D Hand Pose Estimation via Neural Rendering](https://mlsanity.com/paper/1904.04196/) (2019)

## Abstract (arXiv)

Deterministic models for 3D hand pose reconstruction, whether single-staged or cascaded, struggle with pose ambiguities caused by self-occlusions and complex hand articulations. Existing cascaded approaches progressively refine pose predictions in a coarse-to-fine manner, but their deterministic nature prevents them from modeling pose uncertainty. Conversely, recent probabilistic methods capture pose distributions but are confined to single-stage estimation, often yielding inaccurate 3D reconstructions without refinement. To address these limitations, we propose a coarse-to-fine cascaded diffusion framework that combines probabilistic modeling with cascaded refinement. The first stage is a joint diffusion model that samples diverse 3D joint hypotheses, and the second stage is a Mesh Latent Diffusion Model (Mesh LDM) that reconstructs a 3D hand mesh conditioned on a joint sample. Our key idea is to use these diverse hypotheses as a training signal rather than as final outputs, so that the Mesh LDM learns distribution-aware joint-mesh relationships and becomes robust to the variation in coarse predictions. Extensive ablations validate the necessity of the cascaded design and the choice of latent-space diffusion. Experiments on FreiHAND, HO3Dv2, and DexYCB show that our method achieves state-of-the-art performance and remains stable under occlusion and pose ambiguity.