DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
Moon-bow
Abstract
DPoser-X, a diffusion-based model, addresses the complexity of 3D human poses using variational diffusion sampling and a novel truncated timestep scheduling method, outperforming existing models across various pose benchmarks.
We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent complexity of articulated human poses and the scarcity of high-quality whole-body pose datasets. To address these limitations, we introduce a Diffusion model as body Pose prior (DPoser) and extend it to DPoser-X for expressive whole-body human pose modeling. Our approach unifies various pose-centric tasks as inverse problems, solving them through variational diffusion sampling. To enhance performance on downstream applications, we introduce a novel truncated timestep scheduling method specifically designed for pose data characteristics. We also propose a masked training mechanism that effectively combines whole-body and part-specific datasets, enabling our model to capture interdependencies between body parts while avoiding overfitting to specific actions. Extensive experiments demonstrate DPoser-X's robustness and versatility across multiple benchmarks for body, hand, face, and full-body pose modeling. Our model consistently outperforms state-of-the-art alternatives, establishing a new benchmark for whole-body human pose prior modeling.
Community
🚨 Revolutionary 3D Human Pose Prior is here!
We introduce DPoser-X — the first diffusion-based robust 3D whole-body human pose prior.
🤖 Current pose priors like VPoser and NDFs struggle with diversity and realism across body parts.
So we built a diffusion-based pose prior model that:
🧬 Leverages unconditional diffusion models as robust pose priors
🔁 Solves pose-centric tasks through a unified optimization framework
📉 Uses truncated timestep scheduling optimized for pose data
🎯 Employs mixed training strategy for advanced whole-body pose modeling
Result? A versatile prior that works across ALL pose-related tasks.
📊 Up to 61% improvement across 8 benchmarks, outperforming all existing alternatives.
📚 Paper: https://arxiv.org/abs/2508.00599
💻 Code: https://github.com/careless-lu/DPoser
🌐 Project: https://dposer.github.io/
🎥 Demo: https://youtu.be/yzwliadFcX0
🎉 Accepted as ICCV 2025 Oral!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- MaskHOI: Robust 3D Hand-Object Interaction Estimation via Masked Pre-training (2025)
- Pose-Star: Anatomy-Aware Editing for Open-World Fashion Images (2025)
- StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion (2025)
- Diffusion-based 3D Hand Motion Recovery with Intuitive Physics (2025)
- Towards Consistent Long-Term Pose Generation (2025)
- Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders (2025)
- DiffFit: Disentangled Garment Warping and Texture Refinement for Virtual Try-On (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper